Tutorial of AI Kit with Raspberry Pi From Zero to Hero
- Play your AI Kit from Beginner to Expert -
Report Bug |
Request Feature
In this lesson, we will set up a Raspberry Pi to run image classification using a pre-trained EfficientNet model and a standard dataset.
This guide will walk you through the environment setup, model preparation, and running a live image classification script.
## Prepare Your Raspberry Pi
First, let's create a folder for your TensorFlow course and set up a virtual environment.
```bash
mkdir my_tf_course
cd my_tf_course
python -m venv --system-site-packages env
source env/bin/activate
```
## Install TensorFlow and OpenCV
```bash
pip3 install opencv-contrib-python tensorflow
```
## Download the EfficientNet Model and Labels
Download the [EfficientNet pre-trained model](../../models/Chapter2/2.tflite) and the [imagenet-classes.txt](../../models/Chapter2/imagenet-classes.txt) file (which contains the labels).
Copy these files to a folder on your Desktop named `tf_files`.
## Create the Python Script
```bash
import os
import cv2
import numpy as np
import tensorflow as tf
# Define paths as variables
MODEL_PATH = os.path.expanduser("/home/pi/Desktop/tf_files/2.tflite") # Adjust as needed
LABELS_PATH = os.path.expanduser("/home/pi/Desktop/tf_files/imagenet-classes.txt") # Adjust as needed
# Load the TFLite model
interpreter = tf.lite.Interpreter(model_path=MODEL_PATH)
interpreter.allocate_tensors()
# Get input and output details for the model
input_details = interpreter.get_input_details()
output_details = interpreter.get_output_details()
# Load labels (assuming they are in a text file, one label per line)
with open(LABELS_PATH, 'r') as f:
labels = [line.strip() for line in f.readlines()]
# Function to preprocess image
def preprocess_image(image):
image = cv2.resize(image, (224, 224))
image = np.expand_dims(image, axis=0).astype(np.uint8)
return image
# Function to get top 3 predictions
def get_top_3_predictions(interpreter, image):
interpreter.set_tensor(input_details[0]['index'], image)
interpreter.invoke()
output = interpreter.get_tensor(output_details[0]['index'])
output = np.squeeze(output)
top_3_indices = output.argsort()[-3:][::-1]
return top_3_indices, output[top_3_indices]
# Start webcam capture
cap = cv2.VideoCapture(0)
while True:
ret, frame = cap.read()
if not ret:
break
image = preprocess_image(frame)
top_3_indices, top_3_probs = get_top_3_predictions(interpreter, image)
# Display the predictions with class names
for i, (idx, prob) in enumerate(zip(top_3_indices, top_3_probs)):
label = labels[idx] if idx < len(labels) else "Unknown"
cv2.putText(frame, f"Top {i+1}: {label} ({prob:.2f})", (10, 30 + i * 30),
cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 0, 0), 2)
cv2.imshow('Webcam Feed - Top 3 Predictions', frame)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
cap.release()
cv2.destroyAllWindows()
```
## Run the Script
Navigate to the folder where your Python file (tflesson1.py) is saved.
```bash
cd /home/pi/Desktop/tf_files
```
Run the Python script to start the webcam feed with predictions.
```bash
python tflesson1.py
```
================================================
FILE: articles/Chapter_2-Configuring_the_RaspberryPi_Environment/Introduction_to_Ultralytics_in_Raspberry_Pi_Environment.md
================================================
---
sidebar_position: 4
---
# Introduction to Ultralytics in Raspberry Pi Environment
## Who is Ultralytics?
[Ultralytics](https://www.ultralytics.com/) is a company and open-source organization known for developing YOLOv5 and YOLOv8,YOLO11 popular deep learning models for real-time object detection. YOLO, short for "You Only Look Once," is a family of object detection models designed for high-speed, accurate detection in images and video. Ultralytics has made significant contributions to YOLO by optimizing its models for both performance and accessibility, making it popular in applications like surveillance, autonomous vehicles, robotics, and more.
Ultralytics offers a diverse suite of models designed for specialized tasks such as **object detection, instance segmentation, image classification, pose estimation, and multi-object tracking.**
**YOLO11** Ultralytics’ latest YOLO series delivers state-of-the-art (SOTA) performance across various tasks.
In this tutorial, we’ll explore deploying YOLO11 on a Raspberry Pi. In the next tutorial, we’ll dive into how to harness this remarkable architecture using the Hailo Accelerator.
## Ultralytics on Raspberry Pi Environment
### Step 1: Train and Export the Model
**Ultralytics** provides the **COCO dataset** labels, which can be used to train the model. Initially, the model weights are provided in .pt format. To use the model on resource-constrained devices like the Raspberry Pi, we need to convert the weights into a quantized format.
For this, you can use the following Colab code to convert the model to a **TensorFlow Lite (TFLite)** format. In this case, we will train the **YOLO11n** model with an image size of 224x224, and then convert the trained model into the TFLite format for efficient deployment on the Raspberry Pi.
After running each cell in the Colab notebook, you'll generate two TFLite model files: one with 32-bit floating-point precision and the other with 16-bit precision. You can test either of these, but for this example, we will proceed with the 16-bit floating-point model. Download this file to continue.
Let's Go to Raspberry Pi
### Step 2: Set Up a Project Directory
```bash
mkdir my_ultralytics
cd my_ultralytics
```
### Step 3: Create a Virtual Environment and Activate the virtual environment
```bash
python -m venv --system-site-packages env
source env/bin/activate
```
### Step 4: Install Required Libraries
```bash
pip install ultralytics tensorflow
sudo reboot
```
### Step 5: Set Up the Code
**Open Thonny Python IDE** and paste the following code snippet. Save the file on your desktop in a folder named `Yolo_Files` with the filename `test_yolo_coco.py`:
```bash
import cv2
import time
from ultralytics import YOLO
# Load COCO class names
with open("coco.txt", "r") as f:
class_names = f.read().splitlines()
# Load the YOLOv8 model (TFLite version)
model = YOLO("best_float16.tflite")
# Open the webcam
cap = cv2.VideoCapture(0)
count = 0
# Initialize variables for FPS calculation
prev_time = 0
while True:
ret, frame = cap.read()
if not ret:
break
count += 1
if count % 3 != 0:
continue
current_time = time.time()
# Run YOLOv8 detection on the frame
results = model(frame, conf=0.7, imgsz=224)
for result in results:
boxes = result.boxes
for box in boxes:
x1, y1, x2, y2 = map(int, box.xyxy[0])
confidence = box.conf[0]
class_id = int(box.cls[0])
class_name = class_names[class_id]
# Draw the bounding box
cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 255, 0), 2)
# Label the detection
label = f'{class_name} {confidence:.2f}'
cv2.putText(frame, label, (x1, y1 - 5), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0), 2)
# Calculate and display FPS
fps = 1 / (current_time - prev_time)
prev_time = current_time
cv2.putText(frame, f'FPS: {fps:.2f}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
# Display the frame
cv2.imshow("Webcam", frame)
if cv2.waitKey(1) & 0xFF == ord("q"):
break
cap.release()
cv2.destroyAllWindows()
```
### Step 6: Download the Necessary Files
Save the following files in the Yolo_Files folder
- **best_float16.tflite**: [The TFLite mode](../../models/Chapter2/best_float16.tflite) file.
- **coco.txt**: A text file containing the [COCO dataset labels](../../models/Chapter2/coco.txt).
### Step 7: Activate the virtual Environment
```bash
cd my_ultralytics
source env/bin/activate
```
### Step 8: Run the YOLOv8 Model
Navigate to the Yolo_Files folder and Run the Python script
```bash
cd /home/pi/Desktop/Yolo_Files
python test_yolo_coco.py
```
Press `q` to quit the application while it’s running.
You may notice a slight delay in the FPS (frames per second) while running this model, as it relies on the Raspberry Pi’s CPU for inference. CPU-only mode can limit real-time performance, making it challenging for tasks that require quick responsiveness. This is where the **Hailo accelerator** (the AI Kit for Raspberry Pi) becomes essential, offering optimized processing that enhances real-time performance for applications like object detection, tracking, and other AI-driven tasks.
## Other Resources
[Quick Start Guide: Raspberry Pi with Ultralytics YOLO11](https://docs.ultralytics.com/guides/raspberry-pi/)
[Model Export with Ultralytics YOLO](https://docs.ultralytics.com/modes/export/)
[A Guide on YOLO11 Model Export to TFLite for Deployment](https://docs.ultralytics.com/integrations/tflite/#deployment-options-in-tflite)
================================================
FILE: articles/Chapter_2-Configuring_the_RaspberryPi_Environment/index.md
================================================
---
title: Chapter 2 - Configuring the Raspberry Pi Environment
---
================================================
FILE: articles/Chapter_3-Computer_Vision_Projects_and_Practical_Applications/.gitkeep
================================================
================================================
FILE: articles/Chapter_3-Computer_Vision_Projects_and_Practical_Applications/Accelerating_the_MediaPipe_models_with_Hailo_NPU.md
================================================
---
sidebar_position: 4
---
# Accelerating the MediaPipe models with Hailo NPU
## Overview
[MediaPipe](https://github.com/google-ai-edge/mediapipe) is an open-source framework created by Google for constructing machine learning pipelines that handle time-series data, including video and audio. It provides customizable solutions for a wide range of applications, particularly in computer vision and on-device machine learning tasks.
This article outlines the process of deploying a MediaPipe model on an AI Box to enhance hand detection, gesture landmarks, and face landmarks.
## Prepare Hardware
> **Note:**
> Please connect a USB camera to the AI Box.
| reComputer AI R2130 |
|---|
 |
| reComputer AI Industrial R2000 | reComputer AI R2000 |
|---|---|
 |
|
Note: You need a USB camera as the input.
## Install Hailo Software & Verify Installation
### update the system
```bash
sudo apt update
sudo apt full-upgrade
```
:::note
Sometimes you may encounter the following issues during updates.
```
Get:1 http://deb.debian.org/debian bookworm InRelease [151 kB]
Get:2 http://deb.debian.org/debian-security bookworm-security InRelease [48.0 kB]
Get:3 http://deb.debian.org/debian bookworm-updates InRelease [55.4 kB]
Get:4 http://archive.raspberrypi.com/debian bookworm InRelease [39.0 kB]
Reading package lists... Done
E: Release file for http://deb.debian.org/debian/dists/bookworm/InRelease is not valid yet (invalid for another 58d 8h 26min 35s). Updates for this repository will not be applied.
E: Release file for http://deb.debian.org/debian-security/dists/bookworm-security/InRelease is not valid yet (invalid for another 84d 18h 23min 59s). Updates for this repository will not be applied.
E: Release file for http://archive.raspberrypi.com/debian/dists/bookworm/InRelease is not valid yet (invalid for another 84d 13h 13min 5s). Updates for this repository will not be applied.
E: Release file for http://deb.debian.org/debian/dists/bookworm-updates/InRelease is not valid yet (invalid for another 85d 0h 52min 29s). Updates for this repository will not be applied.
```
This is because the time on the Raspberry Pi is set incorrectly, and you need to manually set the time on the Raspberry Pi with command below:
```
# This command only you can connect google.com
sudo date -s "$(wget -qSO- --max-redirect=0 google.com 2>&1 | grep Date: | cut -d' ' -f5-8)Z"
```
After set your raspberry time, you can update your raspberry.
:::
### Set pcie to gen2/gen3(gen3 is faster than gen2)
Add following text to ```/boot/firmware/config.txt```
```bash
# Enable the PCIe external connector
dtparam=pciex1
# Force Gen 3.0 speeds
dtparam=pciex1_gen=3
```
:::note
If you want to use gen2, please comment dtparam=pciex1_gen=3
:::
### Install hailo-all and reboot
Open terminal on the Raspberry Pi5, and input command as follows to install Hailo software.
```bash
sudo apt install hailo-all
sudo apt-get -y install libblas-dev nlohmann-json3-dev
sudo reboot
```
### Check Software and Hardware
Open terminal on the Raspberry Pi5, and input command as follows to check if hailo-all have been installed.
```bash
hailortcli fw-control identify
```
The right result show as bellow:
Note: Place the photo of the person to be recognized into the folder that was just created.
### Add information to the database
```bash
cd ~/hailo-apps-infra/hailo_apps/hailo_app_python/apps/face_recognition
python face_recognition.py --mode train
```
The right result show as bellow:
| reComputer AI R2130 |
|---|
|
| reComputer AI R2130 |
|---|
|
![\"Open](\"https://colab.research.google.com/assets/colab-badge.svg\"){kind=icon}
"
]
},
{
"cell_type": "markdown",
"source": [
"### Import relevent libraries"
],
"metadata": {
"id": "opjlCMX-p9Cq"
}
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "9AVZCC4FpzmE"
},
"outputs": [],
"source": [
"import tensorflow as tf\n",
"\n",
"from tensorflow.keras import datasets, layers, models\n",
"import matplotlib.pyplot as plt"
]
},
{
"cell_type": "code",
"source": [
"(train_images, train_labels), (test_images, test_labels) = datasets.cifar10.load_data()\n",
"\n",
"# Normalize pixel values to be between 0 and 1\n",
"train_images, test_images = train_images / 255.0, test_images / 255.0"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "d2xcCVTvrIf0",
"outputId": "0212e9b8-539a-476b-891d-06af8bab10d0"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Downloading data from https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz\n",
"\u001b[1m170498071/170498071\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 0us/step\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"class_names = ['airplane', 'automobile', 'bird', 'cat', 'deer',\n",
" 'dog', 'frog', 'horse', 'ship', 'truck']\n",
"\n",
"plt.figure(figsize=(10,10))\n",
"for i in range(25):\n",
" plt.subplot(5,5,i+1)\n",
" plt.xticks([])\n",
" plt.yticks([])\n",
" plt.grid(False)\n",
" plt.imshow(train_images[i])\n",
" # The CIFAR labels happen to be arrays,\n",
" # which is why you need the extra index\n",
" plt.xlabel(class_names[train_labels[i][0]])\n",
"plt.show()"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 826
},
"id": "V4TQNKWmrXgR",
"outputId": "cfe2398a-8687-407f-9151-fe15a3d3035f"
},
"execution_count": null,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"Model: \"sequential\"\n",
"\n"
]
},
"metadata": {}
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓\n",
"┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
"┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩\n",
"│ conv2d (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m30\u001b[0m, \u001b[38;5;34m30\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m896\u001b[0m │\n",
"├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
"│ max_pooling2d (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m15\u001b[0m, \u001b[38;5;34m15\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n",
"├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
"│ conv2d_1 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m13\u001b[0m, \u001b[38;5;34m13\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m18,496\u001b[0m │\n",
"├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
"│ max_pooling2d_1 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m6\u001b[0m, \u001b[38;5;34m6\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n",
"├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
"│ conv2d_2 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m36,928\u001b[0m │\n",
"└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘\n"
],
"text/html": [
"┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓\n",
"┃ Layer (type) ┃ Output Shape ┃ Param # ┃\n",
"┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩\n",
"│ conv2d (Conv2D) │ (None, 30, 30, 32) │ 896 │\n",
"├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
"│ max_pooling2d (MaxPooling2D) │ (None, 15, 15, 32) │ 0 │\n",
"├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
"│ conv2d_1 (Conv2D) │ (None, 13, 13, 64) │ 18,496 │\n",
"├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
"│ max_pooling2d_1 (MaxPooling2D) │ (None, 6, 6, 64) │ 0 │\n",
"├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
"│ conv2d_2 (Conv2D) │ (None, 4, 4, 64) │ 36,928 │\n",
"└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘\n",
"\n"
]
},
"metadata": {}
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"\u001b[1m Total params: \u001b[0m\u001b[38;5;34m56,320\u001b[0m (220.00 KB)\n"
],
"text/html": [
"Total params: 56,320 (220.00 KB)\n", "\n" ] }, "metadata": {} }, { "output_type": "display_data", "data": { "text/plain": [ "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m56,320\u001b[0m (220.00 KB)\n" ], "text/html": [ "
Trainable params: 56,320 (220.00 KB)\n", "\n" ] }, "metadata": {} }, { "output_type": "display_data", "data": { "text/plain": [ "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n" ], "text/html": [ "
Non-trainable params: 0 (0.00 B)\n", "\n" ] }, "metadata": {} } ] }, { "cell_type": "code", "source": [ "model.add(layers.Flatten())\n", "model.add(layers.Dense(64, activation='relu'))\n", "model.add(layers.Dense(10))" ], "metadata": { "id": "PSnEoZzlr8Vd" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "model.summary()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 385 }, "id": "sLoPYY0RsIFx", "outputId": "bf7200e9-a9d2-4cce-eee3-0abff67143bf" }, "execution_count": null, "outputs": [ { "output_type": "display_data", "data": { "text/plain": [ "\u001b[1mModel: \"sequential\"\u001b[0m\n" ], "text/html": [ "
Model: \"sequential\"\n",
"\n"
]
},
"metadata": {}
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓\n",
"┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
"┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩\n",
"│ conv2d (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m30\u001b[0m, \u001b[38;5;34m30\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m896\u001b[0m │\n",
"├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
"│ max_pooling2d (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m15\u001b[0m, \u001b[38;5;34m15\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n",
"├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
"│ conv2d_1 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m13\u001b[0m, \u001b[38;5;34m13\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m18,496\u001b[0m │\n",
"├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
"│ max_pooling2d_1 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m6\u001b[0m, \u001b[38;5;34m6\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n",
"├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
"│ conv2d_2 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m36,928\u001b[0m │\n",
"├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
"│ flatten (\u001b[38;5;33mFlatten\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1024\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n",
"├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
"│ dense (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m65,600\u001b[0m │\n",
"├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
"│ dense_1 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m) │ \u001b[38;5;34m650\u001b[0m │\n",
"└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘\n"
],
"text/html": [
"┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓\n",
"┃ Layer (type) ┃ Output Shape ┃ Param # ┃\n",
"┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩\n",
"│ conv2d (Conv2D) │ (None, 30, 30, 32) │ 896 │\n",
"├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
"│ max_pooling2d (MaxPooling2D) │ (None, 15, 15, 32) │ 0 │\n",
"├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
"│ conv2d_1 (Conv2D) │ (None, 13, 13, 64) │ 18,496 │\n",
"├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
"│ max_pooling2d_1 (MaxPooling2D) │ (None, 6, 6, 64) │ 0 │\n",
"├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
"│ conv2d_2 (Conv2D) │ (None, 4, 4, 64) │ 36,928 │\n",
"├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
"│ flatten (Flatten) │ (None, 1024) │ 0 │\n",
"├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
"│ dense (Dense) │ (None, 64) │ 65,600 │\n",
"├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
"│ dense_1 (Dense) │ (None, 10) │ 650 │\n",
"└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘\n",
"\n"
]
},
"metadata": {}
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"\u001b[1m Total params: \u001b[0m\u001b[38;5;34m122,570\u001b[0m (478.79 KB)\n"
],
"text/html": [
"Total params: 122,570 (478.79 KB)\n", "\n" ] }, "metadata": {} }, { "output_type": "display_data", "data": { "text/plain": [ "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m122,570\u001b[0m (478.79 KB)\n" ], "text/html": [ "
Trainable params: 122,570 (478.79 KB)\n", "\n" ] }, "metadata": {} }, { "output_type": "display_data", "data": { "text/plain": [ "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n" ], "text/html": [ "
Non-trainable params: 0 (0.00 B)\n", "\n" ] }, "metadata": {} } ] }, { "cell_type": "code", "source": [ "model.compile(optimizer='adam',\n", " loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),\n", " metrics=['accuracy'])\n", "\n", "history = model.fit(train_images, train_labels, epochs=10,\n", " validation_data=(test_images, test_labels))" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "7Oi_9aAbsVya", "outputId": "f08abd98-2d91-421a-de5b-91ef9d417972" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Epoch 1/10\n", "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m73s\u001b[0m 45ms/step - accuracy: 0.3617 - loss: 1.7323 - val_accuracy: 0.5535 - val_loss: 1.2656\n", "Epoch 2/10\n", "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m81s\u001b[0m 44ms/step - accuracy: 0.5757 - loss: 1.1888 - val_accuracy: 0.6002 - val_loss: 1.1064\n", "Epoch 3/10\n", "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m80s\u001b[0m 43ms/step - accuracy: 0.6533 - loss: 0.9891 - val_accuracy: 0.6420 - val_loss: 1.0434\n", "Epoch 4/10\n", "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m70s\u001b[0m 45ms/step - accuracy: 0.6892 - loss: 0.8790 - val_accuracy: 0.6854 - val_loss: 0.8979\n", "Epoch 5/10\n", "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m80s\u001b[0m 44ms/step - accuracy: 0.7197 - loss: 0.7991 - val_accuracy: 0.6717 - val_loss: 0.9365\n", "Epoch 6/10\n", "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m82s\u001b[0m 44ms/step - accuracy: 0.7366 - loss: 0.7426 - val_accuracy: 0.6990 - val_loss: 0.8640\n", "Epoch 7/10\n", "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m81s\u001b[0m 44ms/step - accuracy: 0.7579 - loss: 0.6840 - val_accuracy: 0.6711 - val_loss: 0.9963\n", "Epoch 8/10\n", "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m83s\u001b[0m 44ms/step - accuracy: 0.7754 - loss: 0.6380 - val_accuracy: 0.7121 - val_loss: 0.8427\n", "Epoch 9/10\n", "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m80s\u001b[0m 44ms/step - accuracy: 0.7976 - loss: 0.5824 - val_accuracy: 0.7090 - val_loss: 0.8609\n", "Epoch 10/10\n", "\u001b[1m1563/1563\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m82s\u001b[0m 44ms/step - accuracy: 0.8096 - loss: 0.5404 - val_accuracy: 0.7060 - val_loss: 0.9005\n" ] } ] }, { "cell_type": "code", "source": [ "plt.plot(history.history['accuracy'], label='accuracy')\n", "plt.plot(history.history['val_accuracy'], label = 'val_accuracy')\n", "plt.xlabel('Epoch')\n", "plt.ylabel('Accuracy')\n", "plt.ylim([0.5, 1])\n", "plt.legend(loc='lower right')\n", "\n", "test_loss, test_acc = model.evaluate(test_images, test_labels, verbose=2)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 472 }, "id": "UqE-3urKsh61", "outputId": "b2a46e52-5e94-47be-d31d-cd4edbb66c41" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "313/313 - 3s - 11ms/step - accuracy: 0.7060 - loss: 0.9005\n" ] }, { "output_type": "display_data", "data": { "text/plain": [ "
"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "5iPPYi43UUrQ",
"outputId": "ce555e57-28de-4943-a2c4-400e279847c6"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Python 3.10.12\n"
]
}
],
"source": [
"! python -V"
]
},
{
"cell_type": "code",
"source": [
"! pip install ultralytics"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "SQDdjjDhVym-",
"outputId": "cb37dafb-cf1f-4bca-d392-80ed58579238"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Collecting ultralytics\n",
" Downloading ultralytics-8.3.29-py3-none-any.whl.metadata (35 kB)\n",
"Requirement already satisfied: numpy>=1.23.0 in /usr/local/lib/python3.10/dist-packages (from ultralytics) (1.26.4)\n",
"Requirement already satisfied: matplotlib>=3.3.0 in /usr/local/lib/python3.10/dist-packages (from ultralytics) (3.8.0)\n",
"Requirement already satisfied: opencv-python>=4.6.0 in /usr/local/lib/python3.10/dist-packages (from ultralytics) (4.10.0.84)\n",
"Requirement already satisfied: pillow>=7.1.2 in /usr/local/lib/python3.10/dist-packages (from ultralytics) (11.0.0)\n",
"Requirement already satisfied: pyyaml>=5.3.1 in /usr/local/lib/python3.10/dist-packages (from ultralytics) (6.0.2)\n",
"Requirement already satisfied: requests>=2.23.0 in /usr/local/lib/python3.10/dist-packages (from ultralytics) (2.32.3)\n",
"Requirement already satisfied: scipy>=1.4.1 in /usr/local/lib/python3.10/dist-packages (from ultralytics) (1.13.1)\n",
"Requirement already satisfied: torch>=1.8.0 in /usr/local/lib/python3.10/dist-packages (from ultralytics) (2.5.0+cu121)\n",
"Requirement already satisfied: torchvision>=0.9.0 in /usr/local/lib/python3.10/dist-packages (from ultralytics) (0.20.0+cu121)\n",
"Requirement already satisfied: tqdm>=4.64.0 in /usr/local/lib/python3.10/dist-packages (from ultralytics) (4.66.6)\n",
"Requirement already satisfied: psutil in /usr/local/lib/python3.10/dist-packages (from ultralytics) (5.9.5)\n",
"Requirement already satisfied: py-cpuinfo in /usr/local/lib/python3.10/dist-packages (from ultralytics) (9.0.0)\n",
"Requirement already satisfied: pandas>=1.1.4 in /usr/local/lib/python3.10/dist-packages (from ultralytics) (2.2.2)\n",
"Requirement already satisfied: seaborn>=0.11.0 in /usr/local/lib/python3.10/dist-packages (from ultralytics) (0.13.2)\n",
"Collecting ultralytics-thop>=2.0.0 (from ultralytics)\n",
" Downloading ultralytics_thop-2.0.11-py3-none-any.whl.metadata (9.4 kB)\n",
"Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.3.0->ultralytics) (1.3.0)\n",
"Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.3.0->ultralytics) (0.12.1)\n",
"Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.3.0->ultralytics) (4.54.1)\n",
"Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.3.0->ultralytics) (1.4.7)\n",
"Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.3.0->ultralytics) (24.2)\n",
"Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.3.0->ultralytics) (3.2.0)\n",
"Requirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.3.0->ultralytics) (2.8.2)\n",
"Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas>=1.1.4->ultralytics) (2024.2)\n",
"Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.10/dist-packages (from pandas>=1.1.4->ultralytics) (2024.2)\n",
"Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.23.0->ultralytics) (3.4.0)\n",
"Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.23.0->ultralytics) (3.10)\n",
"Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.23.0->ultralytics) (2.2.3)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.23.0->ultralytics) (2024.8.30)\n",
"Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from torch>=1.8.0->ultralytics) (3.16.1)\n",
"Requirement already satisfied: typing-extensions>=4.8.0 in /usr/local/lib/python3.10/dist-packages (from torch>=1.8.0->ultralytics) (4.12.2)\n",
"Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.8.0->ultralytics) (3.4.2)\n",
"Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch>=1.8.0->ultralytics) (3.1.4)\n",
"Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from torch>=1.8.0->ultralytics) (2024.10.0)\n",
"Requirement already satisfied: sympy==1.13.1 in /usr/local/lib/python3.10/dist-packages (from torch>=1.8.0->ultralytics) (1.13.1)\n",
"Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.10/dist-packages (from sympy==1.13.1->torch>=1.8.0->ultralytics) (1.3.0)\n",
"Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.7->matplotlib>=3.3.0->ultralytics) (1.16.0)\n",
"Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch>=1.8.0->ultralytics) (3.0.2)\n",
"Downloading ultralytics-8.3.29-py3-none-any.whl (883 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m883.8/883.8 kB\u001b[0m \u001b[31m45.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading ultralytics_thop-2.0.11-py3-none-any.whl (26 kB)\n",
"Installing collected packages: ultralytics-thop, ultralytics\n",
"Successfully installed ultralytics-8.3.29 ultralytics-thop-2.0.11\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"from ultralytics import YOLO"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "zWMJjMG4V347",
"outputId": "b8e645c8-2035-4ace-bb87-ab0487489336"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Creating new Ultralytics Settings v0.0.6 file ✅ \n",
"View Ultralytics Settings with 'yolo settings' or at '/root/.config/Ultralytics/settings.json'\n",
"Update Settings with 'yolo settings key=value', i.e. 'yolo settings runs_dir=path/to/dir'. For help see https://docs.ultralytics.com/quickstart/#ultralytics-settings.\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"model = YOLO(\"yolo11n.pt\")"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "_vNi1L8hWH4Y",
"outputId": "a2ddc00a-af52-4657-9a93-bcf01e055d87"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Downloading https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11n.pt to 'yolo11n.pt'...\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"100%|██████████| 5.35M/5.35M [00:00<00:00, 325MB/s]\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"# Train the model\n",
"train_results = model.train(\n",
" data=\"coco8.yaml\", # path to dataset YAML\n",
" epochs=100, # number of training epochs\n",
" imgsz=224, # training image size\n",
" )"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "FllQC1rDWH78",
"outputId": "273eae24-e37d-40a2-d605-d8713688cba2"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Ultralytics 8.3.29 🚀 Python-3.10.12 torch-2.5.0+cu121 CUDA:0 (Tesla T4, 15102MiB)\n",
"\u001b[34m\u001b[1mengine/trainer: \u001b[0mtask=detect, mode=train, model=yolo11n.pt, data=coco8.yaml, epochs=100, time=None, patience=100, batch=16, imgsz=224, save=True, save_period=-1, cache=False, device=None, workers=8, project=None, name=train, exist_ok=False, pretrained=True, optimizer=auto, verbose=True, seed=0, deterministic=True, single_cls=False, rect=False, cos_lr=False, close_mosaic=10, resume=False, amp=True, fraction=1.0, profile=False, freeze=None, multi_scale=False, overlap_mask=True, mask_ratio=4, dropout=0.0, val=True, split=val, save_json=False, save_hybrid=False, conf=None, iou=0.7, max_det=300, half=False, dnn=False, plots=True, source=None, vid_stride=1, stream_buffer=False, visualize=False, augment=False, agnostic_nms=False, classes=None, retina_masks=False, embed=None, show=False, save_frames=False, save_txt=False, save_conf=False, save_crop=False, show_labels=True, show_conf=True, show_boxes=True, line_width=None, format=torchscript, keras=False, optimize=False, int8=False, dynamic=False, simplify=True, opset=None, workspace=4, nms=False, lr0=0.01, lrf=0.01, momentum=0.937, weight_decay=0.0005, warmup_epochs=3.0, warmup_momentum=0.8, warmup_bias_lr=0.1, box=7.5, cls=0.5, dfl=1.5, pose=12.0, kobj=1.0, label_smoothing=0.0, nbs=64, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, degrees=0.0, translate=0.1, scale=0.5, shear=0.0, perspective=0.0, flipud=0.0, fliplr=0.5, bgr=0.0, mosaic=1.0, mixup=0.0, copy_paste=0.0, copy_paste_mode=flip, auto_augment=randaugment, erasing=0.4, crop_fraction=1.0, cfg=None, tracker=botsort.yaml, save_dir=runs/detect/train\n",
"\n",
"Dataset 'coco8.yaml' images not found ⚠️, missing path '/content/datasets/coco8/images/val'\n",
"Downloading https://ultralytics.com/assets/coco8.zip to '/content/datasets/coco8.zip'...\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"100%|██████████| 433k/433k [00:00<00:00, 45.3MB/s]\n",
"Unzipping /content/datasets/coco8.zip to /content/datasets/coco8...: 100%|██████████| 25/25 [00:00<00:00, 3706.26file/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"Dataset download success ✅ (2.4s), saved to \u001b[1m/content/datasets\u001b[0m\n",
"\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"Downloading https://ultralytics.com/assets/Arial.ttf to '/root/.config/Ultralytics/Arial.ttf'...\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"100%|██████████| 755k/755k [00:00<00:00, 108MB/s]\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" from n params module arguments \n",
" 0 -1 1 464 ultralytics.nn.modules.conv.Conv [3, 16, 3, 2] \n",
" 1 -1 1 4672 ultralytics.nn.modules.conv.Conv [16, 32, 3, 2] \n",
" 2 -1 1 6640 ultralytics.nn.modules.block.C3k2 [32, 64, 1, False, 0.25] \n",
" 3 -1 1 36992 ultralytics.nn.modules.conv.Conv [64, 64, 3, 2] \n",
" 4 -1 1 26080 ultralytics.nn.modules.block.C3k2 [64, 128, 1, False, 0.25] \n",
" 5 -1 1 147712 ultralytics.nn.modules.conv.Conv [128, 128, 3, 2] \n",
" 6 -1 1 87040 ultralytics.nn.modules.block.C3k2 [128, 128, 1, True] \n",
" 7 -1 1 295424 ultralytics.nn.modules.conv.Conv [128, 256, 3, 2] \n",
" 8 -1 1 346112 ultralytics.nn.modules.block.C3k2 [256, 256, 1, True] \n",
" 9 -1 1 164608 ultralytics.nn.modules.block.SPPF [256, 256, 5] \n",
" 10 -1 1 249728 ultralytics.nn.modules.block.C2PSA [256, 256, 1] \n",
" 11 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] \n",
" 12 [-1, 6] 1 0 ultralytics.nn.modules.conv.Concat [1] \n",
" 13 -1 1 111296 ultralytics.nn.modules.block.C3k2 [384, 128, 1, False] \n",
" 14 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] \n",
" 15 [-1, 4] 1 0 ultralytics.nn.modules.conv.Concat [1] \n",
" 16 -1 1 32096 ultralytics.nn.modules.block.C3k2 [256, 64, 1, False] \n",
" 17 -1 1 36992 ultralytics.nn.modules.conv.Conv [64, 64, 3, 2] \n",
" 18 [-1, 13] 1 0 ultralytics.nn.modules.conv.Concat [1] \n",
" 19 -1 1 86720 ultralytics.nn.modules.block.C3k2 [192, 128, 1, False] \n",
" 20 -1 1 147712 ultralytics.nn.modules.conv.Conv [128, 128, 3, 2] \n",
" 21 [-1, 10] 1 0 ultralytics.nn.modules.conv.Concat [1] \n",
" 22 -1 1 378880 ultralytics.nn.modules.block.C3k2 [384, 256, 1, True] \n",
" 23 [16, 19, 22] 1 464912 ultralytics.nn.modules.head.Detect [80, [64, 128, 256]] \n",
"YOLO11n summary: 319 layers, 2,624,080 parameters, 2,624,064 gradients, 6.6 GFLOPs\n",
"\n",
"Transferred 499/499 items from pretrained weights\n",
"\u001b[34m\u001b[1mTensorBoard: \u001b[0mStart with 'tensorboard --logdir runs/detect/train', view at http://localhost:6006/\n",
"Freezing layer 'model.23.dfl.conv.weight'\n",
"\u001b[34m\u001b[1mAMP: \u001b[0mrunning Automatic Mixed Precision (AMP) checks...\n",
"\u001b[34m\u001b[1mAMP: \u001b[0mchecks passed ✅\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\u001b[34m\u001b[1mtrain: \u001b[0mScanning /content/datasets/coco8/labels/train... 4 images, 0 backgrounds, 0 corrupt: 100%|██████████| 4/4 [00:00<00:00, 1755.67it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\u001b[34m\u001b[1mtrain: \u001b[0mNew cache created: /content/datasets/coco8/labels/train.cache\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\u001b[34m\u001b[1malbumentations: \u001b[0mBlur(p=0.01, blur_limit=(3, 7)), MedianBlur(p=0.01, blur_limit=(3, 7)), ToGray(p=0.01, num_output_channels=3, method='weighted_average'), CLAHE(p=0.01, clip_limit=(1.0, 4.0), tile_grid_size=(8, 8))\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"/usr/local/lib/python3.10/dist-packages/albumentations/__init__.py:24: UserWarning: A new version of Albumentations is available: 1.4.21 (you have 1.4.20). Upgrade using: pip install -U albumentations. To disable automatic update checks, set the environment variable NO_ALBUMENTATIONS_UPDATE to 1.\n",
" check_for_updates()\n",
"\u001b[34m\u001b[1mval: \u001b[0mScanning /content/datasets/coco8/labels/val... 4 images, 0 backgrounds, 0 corrupt: 100%|██████████| 4/4 [00:00<00:00, 333.82it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\u001b[34m\u001b[1mval: \u001b[0mNew cache created: /content/datasets/coco8/labels/val.cache\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"Plotting labels to runs/detect/train/labels.jpg... \n",
"\u001b[34m\u001b[1moptimizer:\u001b[0m 'optimizer=auto' found, ignoring 'lr0=0.01' and 'momentum=0.937' and determining best 'optimizer', 'lr0' and 'momentum' automatically... \n",
"\u001b[34m\u001b[1moptimizer:\u001b[0m AdamW(lr=0.000119, momentum=0.9) with parameter groups 81 weight(decay=0.0), 88 weight(decay=0.0005), 87 bias(decay=0.0)\n",
"\u001b[34m\u001b[1mTensorBoard: \u001b[0mmodel graph visualization added ✅\n",
"Image sizes 224 train, 224 val\n",
"Using 2 dataloader workers\n",
"Logging results to \u001b[1mruns/detect/train\u001b[0m\n",
"Starting training for 100 epochs...\n",
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 1/100 0.216G 1.231 4.624 1.406 30 224: 100%|██████████| 1/1 [00:01<00:00, 1.30s/it]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:01<00:00, 1.32s/it]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.446 0.45 0.472 0.279\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 2/100 0.18G 1.778 5.612 1.737 35 224: 100%|██████████| 1/1 [00:00<00:00, 8.95it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 20.16it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.446 0.45 0.479 0.283\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 3/100 0.18G 1.563 4.104 1.529 18 224: 100%|██████████| 1/1 [00:00<00:00, 8.27it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 20.61it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.452 0.45 0.479 0.276\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 4/100 0.182G 1.578 5.192 1.602 32 224: 100%|██████████| 1/1 [00:00<00:00, 7.84it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 20.91it/s]\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.505 0.45 0.569 0.319\n",
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 5/100 0.18G 1.394 4.96 1.469 32 224: 100%|██████████| 1/1 [00:00<00:00, 8.85it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 21.00it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.528 0.45 0.57 0.328\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 6/100 0.18G 1.459 4.972 1.499 29 224: 100%|██████████| 1/1 [00:00<00:00, 3.90it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 21.33it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.542 0.283 0.561 0.313\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 7/100 0.199G 1.542 5.216 1.49 21 224: 100%|██████████| 1/1 [00:00<00:00, 7.08it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 15.30it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.184 0.65 0.526 0.309\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 8/100 0.199G 1.463 4.388 1.522 25 224: 100%|██████████| 1/1 [00:00<00:00, 6.49it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 15.82it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.184 0.65 0.526 0.31\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 9/100 0.199G 1.236 4.386 1.378 27 224: 100%|██████████| 1/1 [00:00<00:00, 4.18it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 13.57it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.212 0.65 0.532 0.294\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 10/100 0.199G 1.625 5.163 1.647 40 224: 100%|██████████| 1/1 [00:00<00:00, 5.78it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 14.21it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.208 0.65 0.54 0.306\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 11/100 0.199G 1.171 3.879 1.355 12 224: 100%|██████████| 1/1 [00:00<00:00, 5.08it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 12.10it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.219 0.65 0.54 0.303\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 12/100 0.199G 1.404 4.06 1.451 26 224: 100%|██████████| 1/1 [00:00<00:00, 8.61it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 19.75it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.243 0.567 0.485 0.284\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 13/100 0.199G 1.581 5.014 1.578 32 224: 100%|██████████| 1/1 [00:00<00:00, 6.35it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 13.86it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.263 0.567 0.485 0.294\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 14/100 0.199G 1.334 4.21 1.51 10 224: 100%|██████████| 1/1 [00:00<00:00, 8.49it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 21.79it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.26 0.567 0.485 0.294\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 15/100 0.199G 1.271 3.967 1.376 28 224: 100%|██████████| 1/1 [00:00<00:00, 8.59it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 16.13it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.26 0.567 0.484 0.297\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 16/100 0.199G 1.785 4.89 1.674 30 224: 100%|██████████| 1/1 [00:00<00:00, 8.38it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 19.94it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.26 0.567 0.498 0.303\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 17/100 0.199G 1.38 4.628 1.527 27 224: 100%|██████████| 1/1 [00:00<00:00, 8.40it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 20.24it/s]\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.26 0.567 0.499 0.302\n",
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 18/100 0.199G 1.254 4.176 1.437 25 224: 100%|██████████| 1/1 [00:00<00:00, 7.76it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 20.51it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.26 0.567 0.499 0.302\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 19/100 0.21G 1.294 4.442 1.422 29 224: 100%|██████████| 1/1 [00:00<00:00, 7.99it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 21.63it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.261 0.567 0.499 0.302\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 20/100 0.201G 1.414 4.119 1.463 39 224: 100%|██████████| 1/1 [00:00<00:00, 11.74it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 21.99it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.261 0.567 0.499 0.302\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 21/100 0.21G 1.189 3.607 1.372 25 224: 100%|██████████| 1/1 [00:00<00:00, 7.62it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 19.93it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.525 0.352 0.525 0.31\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 22/100 0.199G 1.489 4.613 1.496 28 224: 100%|██████████| 1/1 [00:00<00:00, 11.34it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 18.89it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.525 0.352 0.525 0.31\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 23/100 0.21G 1.064 4.349 1.159 12 224: 100%|██████████| 1/1 [00:00<00:00, 7.57it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 22.12it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.265 0.483 0.458 0.273\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 24/100 0.199G 1.5 3.181 1.517 19 224: 100%|██████████| 1/1 [00:00<00:00, 7.74it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 13.64it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.265 0.483 0.458 0.273\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 25/100 0.208G 1.065 4.656 1.333 10 224: 100%|██████████| 1/1 [00:00<00:00, 5.56it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 11.97it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.26 0.483 0.458 0.273\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 26/100 0.199G 1.295 4.958 1.466 29 224: 100%|██████████| 1/1 [00:00<00:00, 5.98it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 15.93it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.26 0.483 0.458 0.273\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 27/100 0.21G 1.393 4.488 1.451 38 224: 100%|██████████| 1/1 [00:00<00:00, 4.77it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 15.47it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.478 0.283 0.458 0.283\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 28/100 0.199G 1.461 3.788 1.386 26 224: 100%|██████████| 1/1 [00:00<00:00, 11.02it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 21.10it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.478 0.283 0.458 0.283\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 29/100 0.21G 1.562 4.678 1.514 37 224: 100%|██████████| 1/1 [00:00<00:00, 8.58it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 22.46it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.284 0.483 0.465 0.287\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 30/100 0.201G 1.367 4.324 1.416 32 224: 100%|██████████| 1/1 [00:00<00:00, 11.38it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 21.67it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.284 0.483 0.465 0.287\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 31/100 0.21G 1.107 3.741 1.333 30 224: 100%|██████████| 1/1 [00:00<00:00, 8.74it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 22.60it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.373 0.483 0.486 0.297\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 32/100 0.199G 1.125 4.04 1.291 16 224: 100%|██████████| 1/1 [00:00<00:00, 9.69it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 20.49it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.373 0.483 0.486 0.297\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 33/100 0.208G 1.696 4.615 1.596 30 224: 100%|██████████| 1/1 [00:00<00:00, 8.62it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 21.75it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.386 0.483 0.486 0.297\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 34/100 0.201G 1.376 3.978 1.438 43 224: 100%|██████████| 1/1 [00:00<00:00, 11.37it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 21.72it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.386 0.483 0.486 0.297\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 35/100 0.21G 1.439 3.614 1.443 41 224: 100%|██████████| 1/1 [00:00<00:00, 8.58it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 21.52it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.387 0.483 0.485 0.297\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 36/100 0.199G 0.9863 3.18 1.236 18 224: 100%|██████████| 1/1 [00:00<00:00, 10.13it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 16.65it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.387 0.483 0.485 0.297\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 37/100 0.21G 1.772 3.222 1.471 20 224: 100%|██████████| 1/1 [00:00<00:00, 8.61it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 21.79it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.388 0.483 0.486 0.314\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 38/100 0.201G 1.397 3.125 1.47 36 224: 100%|██████████| 1/1 [00:00<00:00, 11.59it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 22.12it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.388 0.483 0.486 0.314\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 39/100 0.208G 1.12 3.61 1.409 20 224: 100%|██████████| 1/1 [00:00<00:00, 8.73it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 21.62it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.402 0.483 0.485 0.314\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 40/100 0.199G 1.227 3.515 1.362 24 224: 100%|██████████| 1/1 [00:00<00:00, 8.79it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 21.22it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.402 0.483 0.485 0.314\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 41/100 0.21G 1.26 3.098 1.347 27 224: 100%|██████████| 1/1 [00:00<00:00, 5.76it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 16.27it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.402 0.483 0.485 0.314\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 42/100 0.201G 1.517 3.545 1.531 34 224: 100%|██████████| 1/1 [00:00<00:00, 6.35it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 12.82it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.402 0.483 0.485 0.314\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 43/100 0.21G 1.59 4.444 1.587 43 224: 100%|██████████| 1/1 [00:00<00:00, 5.32it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 12.51it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.388 0.483 0.485 0.297\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 44/100 0.199G 1.145 4.147 1.303 31 224: 100%|██████████| 1/1 [00:00<00:00, 6.64it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 13.75it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.388 0.483 0.485 0.297\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 45/100 0.208G 1.371 2.552 1.394 12 224: 100%|██████████| 1/1 [00:00<00:00, 4.60it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 11.83it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.388 0.483 0.485 0.31\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 46/100 0.201G 1.31 3.946 1.386 37 224: 100%|██████████| 1/1 [00:00<00:00, 11.65it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 20.18it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.388 0.483 0.485 0.31\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 47/100 0.21G 1.041 3.127 1.179 24 224: 100%|██████████| 1/1 [00:00<00:00, 7.57it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 20.61it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.4 0.467 0.483 0.31\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 48/100 0.199G 1.327 2.897 1.462 25 224: 100%|██████████| 1/1 [00:00<00:00, 11.14it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 21.87it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.4 0.467 0.483 0.31\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 49/100 0.21G 1.166 2.917 1.347 21 224: 100%|██████████| 1/1 [00:00<00:00, 7.71it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 21.38it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.399 0.467 0.484 0.297\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 50/100 0.201G 1.345 3.379 1.417 31 224: 100%|██████████| 1/1 [00:00<00:00, 12.09it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 16.30it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.399 0.467 0.484 0.297\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 51/100 0.21G 1.417 2.73 1.397 28 224: 100%|██████████| 1/1 [00:00<00:00, 8.38it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 19.35it/s]\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.386 0.467 0.484 0.281\n",
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 52/100 0.199G 1.172 2.946 1.294 25 224: 100%|██████████| 1/1 [00:00<00:00, 11.51it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 21.71it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.386 0.467 0.484 0.281\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 53/100 0.208G 1.245 2.186 1.286 22 224: 100%|██████████| 1/1 [00:00<00:00, 11.08it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 20.70it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.386 0.467 0.484 0.281\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 54/100 0.208G 1.317 2.848 1.353 15 224: 100%|██████████| 1/1 [00:00<00:00, 8.62it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 17.11it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.386 0.467 0.484 0.281\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 55/100 0.199G 1.375 2.901 1.44 27 224: 100%|██████████| 1/1 [00:00<00:00, 12.04it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 21.38it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.386 0.467 0.484 0.281\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 56/100 0.208G 1.325 2.653 1.4 14 224: 100%|██████████| 1/1 [00:00<00:00, 11.34it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 16.20it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.386 0.467 0.484 0.281\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 57/100 0.21G 1.38 3.261 1.464 28 224: 100%|██████████| 1/1 [00:00<00:00, 8.23it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 20.55it/s]\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.378 0.467 0.484 0.295\n",
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 58/100 0.199G 1.335 3.206 1.376 37 224: 100%|██████████| 1/1 [00:00<00:00, 10.95it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 13.63it/s]\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.378 0.467 0.484 0.295\n",
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 59/100 0.21G 1.155 3.44 1.325 28 224: 100%|██████████| 1/1 [00:00<00:00, 7.98it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 15.28it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.378 0.467 0.484 0.295\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 60/100 0.21G 1.416 2.734 1.451 31 224: 100%|██████████| 1/1 [00:00<00:00, 5.33it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 16.40it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.302 0.467 0.483 0.252\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 61/100 0.199G 1.27 3.37 1.453 40 224: 100%|██████████| 1/1 [00:00<00:00, 7.36it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 11.35it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.302 0.467 0.483 0.252\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 62/100 0.21G 1.211 3.018 1.38 23 224: 100%|██████████| 1/1 [00:00<00:00, 7.06it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 13.61it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.302 0.467 0.483 0.252\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 63/100 0.21G 1.431 3.015 1.39 37 224: 100%|██████████| 1/1 [00:00<00:00, 6.32it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 21.17it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.303 0.467 0.484 0.253\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 64/100 0.199G 1.229 2.107 1.178 21 224: 100%|██████████| 1/1 [00:00<00:00, 11.11it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 14.26it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.303 0.467 0.484 0.253\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 65/100 0.21G 1.149 3.317 1.291 41 224: 100%|██████████| 1/1 [00:00<00:00, 11.62it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 20.07it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.303 0.467 0.484 0.253\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 66/100 0.21G 1.208 3.242 1.362 34 224: 100%|██████████| 1/1 [00:00<00:00, 8.42it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 19.65it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.276 0.467 0.484 0.236\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 67/100 0.199G 1.329 2.201 1.419 17 224: 100%|██████████| 1/1 [00:00<00:00, 11.20it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 20.87it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.276 0.467 0.484 0.236\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 68/100 0.21G 1.371 2.746 1.412 31 224: 100%|██████████| 1/1 [00:00<00:00, 9.35it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 19.42it/s]\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.276 0.467 0.484 0.236\n",
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 69/100 0.21G 1.264 2.675 1.347 37 224: 100%|██████████| 1/1 [00:00<00:00, 7.83it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 21.16it/s]\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.289 0.467 0.483 0.269\n",
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 70/100 0.199G 1.372 2.33 1.349 26 224: 100%|██████████| 1/1 [00:00<00:00, 11.22it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 20.34it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.289 0.467 0.483 0.269\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 71/100 0.21G 1.073 2.597 1.27 24 224: 100%|██████████| 1/1 [00:00<00:00, 10.56it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 20.11it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.289 0.467 0.483 0.269\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 72/100 0.21G 1.05 2.336 1.228 31 224: 100%|██████████| 1/1 [00:00<00:00, 7.34it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 18.64it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.317 0.467 0.483 0.257\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 73/100 0.199G 1.05 2.746 1.189 17 224: 100%|██████████| 1/1 [00:00<00:00, 9.49it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 17.00it/s]\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.317 0.467 0.483 0.257\n",
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 74/100 0.21G 1.3 2.253 1.357 27 224: 100%|██████████| 1/1 [00:00<00:00, 11.60it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 19.99it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.317 0.467 0.483 0.257\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 75/100 0.208G 1.345 1.545 1.584 11 224: 100%|██████████| 1/1 [00:00<00:00, 8.21it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 21.22it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.316 0.467 0.372 0.201\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 76/100 0.199G 1.188 2.261 1.226 28 224: 100%|██████████| 1/1 [00:00<00:00, 6.53it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 13.58it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.316 0.467 0.372 0.201\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 77/100 0.21G 1.032 2.347 1.271 27 224: 100%|██████████| 1/1 [00:00<00:00, 7.93it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 13.98it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.316 0.467 0.372 0.201\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 78/100 0.21G 1.297 2.229 1.284 29 224: 100%|██████████| 1/1 [00:00<00:00, 3.98it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 7.94it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.316 0.467 0.4 0.198\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 79/100 0.199G 1.149 2.635 1.239 27 224: 100%|██████████| 1/1 [00:00<00:00, 5.88it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 10.96it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.316 0.467 0.4 0.198\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 80/100 0.21G 1.173 2.799 1.326 30 224: 100%|██████████| 1/1 [00:00<00:00, 10.91it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 19.35it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.316 0.467 0.4 0.198\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 81/100 0.21G 1.237 2.89 1.347 22 224: 100%|██████████| 1/1 [00:00<00:00, 8.17it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 21.29it/s]\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.317 0.467 0.4 0.199\n",
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 82/100 0.199G 1.095 2.014 1.268 17 224: 100%|██████████| 1/1 [00:00<00:00, 11.27it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 17.95it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.317 0.467 0.4 0.199\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 83/100 0.21G 1.337 3.537 1.513 34 224: 100%|██████████| 1/1 [00:00<00:00, 11.01it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 20.95it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.317 0.467 0.4 0.199\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 84/100 0.21G 1.486 2.747 1.449 33 224: 100%|██████████| 1/1 [00:00<00:00, 7.76it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 17.13it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.289 0.467 0.372 0.185\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 85/100 0.199G 0.8692 2.611 1.157 24 224: 100%|██████████| 1/1 [00:00<00:00, 11.23it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 21.37it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.289 0.467 0.372 0.185\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 86/100 0.21G 1.283 3.633 1.381 57 224: 100%|██████████| 1/1 [00:00<00:00, 11.44it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 17.91it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.289 0.467 0.372 0.185\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 87/100 0.21G 0.8308 2.621 1.138 21 224: 100%|██████████| 1/1 [00:00<00:00, 11.66it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 18.48it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.289 0.467 0.372 0.185\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 88/100 0.21G 1.353 2.999 1.284 43 224: 100%|██████████| 1/1 [00:00<00:00, 7.85it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 19.93it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.288 0.467 0.372 0.185\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 89/100 0.199G 1.14 2.462 1.303 29 224: 100%|██████████| 1/1 [00:00<00:00, 10.34it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 21.10it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.288 0.467 0.372 0.185\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 90/100 0.21G 1.045 2.878 1.27 28 224: 100%|██████████| 1/1 [00:00<00:00, 10.87it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 16.93it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.288 0.467 0.372 0.185\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"Closing dataloader mosaic\n",
"\u001b[34m\u001b[1malbumentations: \u001b[0mBlur(p=0.01, blur_limit=(3, 7)), MedianBlur(p=0.01, blur_limit=(3, 7)), ToGray(p=0.01, num_output_channels=3, method='weighted_average'), CLAHE(p=0.01, clip_limit=(1.0, 4.0), tile_grid_size=(8, 8))\n",
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 91/100 0.208G 0.9595 1.109 1.074 13 224: 100%|██████████| 1/1 [00:00<00:00, 7.36it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 14.68it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.288 0.467 0.372 0.185\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 92/100 0.21G 1.178 1.064 1.033 13 224: 100%|██████████| 1/1 [00:00<00:00, 5.41it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 15.09it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.402 0.483 0.484 0.24\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 93/100 0.199G 1.083 1.041 1.088 13 224: 100%|██████████| 1/1 [00:00<00:00, 8.50it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 13.29it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.402 0.483 0.484 0.24\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 94/100 0.208G 0.878 1.007 0.9803 13 224: 100%|██████████| 1/1 [00:00<00:00, 5.38it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 11.60it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.402 0.483 0.484 0.24\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 95/100 0.208G 0.9466 1.162 1.067 13 224: 100%|██████████| 1/1 [00:00<00:00, 6.55it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 13.04it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.402 0.483 0.484 0.24\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 96/100 0.208G 0.8918 1.17 1.07 13 224: 100%|██████████| 1/1 [00:00<00:00, 5.75it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 13.26it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.402 0.483 0.484 0.239\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 97/100 0.199G 1.024 1.008 1.069 13 224: 100%|██████████| 1/1 [00:00<00:00, 10.12it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 20.71it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.402 0.483 0.484 0.239\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 98/100 0.208G 0.7823 0.9992 1.019 13 224: 100%|██████████| 1/1 [00:00<00:00, 10.84it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 20.72it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.402 0.483 0.484 0.239\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 99/100 0.21G 0.9106 1.278 1.067 13 224: 100%|██████████| 1/1 [00:00<00:00, 11.19it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 19.64it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.402 0.483 0.484 0.239\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" 100/100 0.21G 0.9683 1.129 1.126 13 224: 100%|██████████| 1/1 [00:00<00:00, 8.41it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 20.30it/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.379 0.483 0.484 0.235\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
"100 epochs completed in 0.027 hours.\n",
"Optimizer stripped from runs/detect/train/weights/last.pt, 5.5MB\n",
"Optimizer stripped from runs/detect/train/weights/best.pt, 5.5MB\n",
"\n",
"Validating runs/detect/train/weights/best.pt...\n",
"Ultralytics 8.3.29 🚀 Python-3.10.12 torch-2.5.0+cu121 CUDA:0 (Tesla T4, 15102MiB)\n",
"YOLO11n summary (fused): 238 layers, 2,616,248 parameters, 0 gradients, 6.5 GFLOPs\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 25.73it/s]\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
" all 4 17 0.53 0.45 0.57 0.328\n",
" person 3 10 0.115 0.2 0.176 0.115\n",
" dog 1 1 0.944 1 0.995 0.497\n",
" horse 1 2 0.595 0.5 0.695 0.234\n",
" elephant 1 2 1 0 0.559 0.125\n",
" umbrella 1 1 0.526 1 0.995 0.995\n",
" potted plant 1 1 0 0 0 0\n",
"Speed: 0.1ms preprocess, 4.2ms inference, 0.0ms loss, 1.6ms postprocess per image\n",
"Results saved to \u001b[1mruns/detect/train\u001b[0m\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"path = model.export(format=\"tflite\")"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "oJgTuHnWW4K6",
"outputId": "77eaf47a-1055-4bfe-9f35-60827868de00"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Ultralytics 8.3.29 🚀 Python-3.10.12 torch-2.5.0+cu121 CPU (Intel Xeon 2.00GHz)\n",
"YOLO11n summary (fused): 238 layers, 2,616,248 parameters, 0 gradients, 6.5 GFLOPs\n",
"\n",
"\u001b[34m\u001b[1mPyTorch:\u001b[0m starting from 'runs/detect/train/weights/best.pt' with input shape (1, 3, 224, 224) BCHW and output shape(s) (1, 84, 1029) (5.2 MB)\n",
"\u001b[31m\u001b[1mrequirements:\u001b[0m Ultralytics requirements ['sng4onnx>=1.0.1', 'onnx_graphsurgeon>=0.3.26', 'onnx>=1.12.0', 'onnx2tf>1.17.5,<=1.22.3', 'onnxslim>=0.1.31', 'tflite_support', 'onnxruntime-gpu'] not found, attempting AutoUpdate...\n",
"Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com\n",
"Collecting sng4onnx>=1.0.1\n",
" Downloading sng4onnx-1.0.4-py3-none-any.whl.metadata (4.6 kB)\n",
"Collecting onnx_graphsurgeon>=0.3.26\n",
" Downloading onnx_graphsurgeon-0.5.2-py2.py3-none-any.whl.metadata (8.1 kB)\n",
"Collecting onnx>=1.12.0\n",
" Downloading onnx-1.17.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (16 kB)\n",
"Collecting onnx2tf<=1.22.3,>1.17.5\n",
" Downloading onnx2tf-1.22.3-py3-none-any.whl.metadata (136 kB)\n",
" ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 136.6/136.6 kB 29.2 MB/s eta 0:00:00\n",
"Collecting onnxslim>=0.1.31\n",
" Downloading onnxslim-0.1.39-py3-none-any.whl.metadata (2.9 kB)\n",
"Collecting tflite_support\n",
" Downloading tflite_support-0.4.4-cp310-cp310-manylinux2014_x86_64.whl.metadata (2.4 kB)\n",
"Collecting onnxruntime-gpu\n",
" Downloading onnxruntime_gpu-1.20.0-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl.metadata (4.4 kB)\n",
"Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from onnx_graphsurgeon>=0.3.26) (1.26.4)\n",
"Requirement already satisfied: protobuf>=3.20.2 in /usr/local/lib/python3.10/dist-packages (from onnx>=1.12.0) (4.25.5)\n",
"Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from onnxslim>=0.1.31) (1.13.1)\n",
"Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from onnxslim>=0.1.31) (24.2)\n",
"Requirement already satisfied: absl-py>=0.7.0 in /usr/local/lib/python3.10/dist-packages (from tflite_support) (1.4.0)\n",
"Requirement already satisfied: flatbuffers>=2.0 in /usr/local/lib/python3.10/dist-packages (from tflite_support) (24.3.25)\n",
"Collecting protobuf>=3.20.2 (from onnx>=1.12.0)\n",
" Downloading protobuf-3.20.3-cp310-cp310-manylinux_2_12_x86_64.manylinux2010_x86_64.whl.metadata (679 bytes)\n",
"Collecting sounddevice>=0.4.4 (from tflite_support)\n",
" Downloading sounddevice-0.5.1-py3-none-any.whl.metadata (1.4 kB)\n",
"Collecting pybind11>=2.6.0 (from tflite_support)\n",
" Downloading pybind11-2.13.6-py3-none-any.whl.metadata (9.5 kB)\n",
"Collecting coloredlogs (from onnxruntime-gpu)\n",
" Downloading coloredlogs-15.0.1-py2.py3-none-any.whl.metadata (12 kB)\n",
"Requirement already satisfied: CFFI>=1.0 in /usr/local/lib/python3.10/dist-packages (from sounddevice>=0.4.4->tflite_support) (1.17.1)\n",
"Collecting humanfriendly>=9.1 (from coloredlogs->onnxruntime-gpu)\n",
" Downloading humanfriendly-10.0-py2.py3-none-any.whl.metadata (9.2 kB)\n",
"Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.10/dist-packages (from sympy->onnxslim>=0.1.31) (1.3.0)\n",
"Requirement already satisfied: pycparser in /usr/local/lib/python3.10/dist-packages (from CFFI>=1.0->sounddevice>=0.4.4->tflite_support) (2.22)\n",
"Downloading sng4onnx-1.0.4-py3-none-any.whl (5.9 kB)\n",
"Downloading onnx_graphsurgeon-0.5.2-py2.py3-none-any.whl (56 kB)\n",
" ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 56.4/56.4 kB 176.9 MB/s eta 0:00:00\n",
"Downloading onnx-1.17.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (16.0 MB)\n",
" ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 16.0/16.0 MB 152.0 MB/s eta 0:00:00\n",
"Downloading onnx2tf-1.22.3-py3-none-any.whl (435 kB)\n",
" ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 435.0/435.0 kB 233.4 MB/s eta 0:00:00\n",
"Downloading onnxslim-0.1.39-py3-none-any.whl (141 kB)\n",
" ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 141.8/141.8 kB 217.9 MB/s eta 0:00:00\n",
"Downloading tflite_support-0.4.4-cp310-cp310-manylinux2014_x86_64.whl (60.8 MB)\n",
" ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 60.8/60.8 MB 106.2 MB/s eta 0:00:00\n",
"Downloading onnxruntime_gpu-1.20.0-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (291.5 MB)\n",
" ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 291.5/291.5 MB 137.5 MB/s eta 0:00:00\n",
"Downloading protobuf-3.20.3-cp310-cp310-manylinux_2_12_x86_64.manylinux2010_x86_64.whl (1.1 MB)\n",
" ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.1/1.1 MB 263.4 MB/s eta 0:00:00\n",
"Downloading pybind11-2.13.6-py3-none-any.whl (243 kB)\n",
" ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 243.3/243.3 kB 315.5 MB/s eta 0:00:00\n",
"Downloading sounddevice-0.5.1-py3-none-any.whl (32 kB)\n",
"Downloading coloredlogs-15.0.1-py2.py3-none-any.whl (46 kB)\n",
" ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 46.0/46.0 kB 175.5 MB/s eta 0:00:00\n",
"Downloading humanfriendly-10.0-py2.py3-none-any.whl (86 kB)\n",
" ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 86.8/86.8 kB 230.0 MB/s eta 0:00:00\n",
"Installing collected packages: sng4onnx, pybind11, protobuf, onnx2tf, humanfriendly, sounddevice, onnx, coloredlogs, tflite_support, onnxslim, onnxruntime-gpu, onnx_graphsurgeon\n",
" Attempting uninstall: protobuf\n",
" Found existing installation: protobuf 4.25.5\n",
" Uninstalling protobuf-4.25.5:\n",
" Successfully uninstalled protobuf-4.25.5\n",
"Successfully installed coloredlogs-15.0.1 humanfriendly-10.0 onnx-1.17.0 onnx2tf-1.22.3 onnx_graphsurgeon-0.5.2 onnxruntime-gpu-1.20.0 onnxslim-0.1.39 protobuf-3.20.3 pybind11-2.13.6 sng4onnx-1.0.4 sounddevice-0.5.1 tflite_support-0.4.4\n",
"\n",
"\u001b[31m\u001b[1mrequirements:\u001b[0m AutoUpdate success ✅ 28.8s, installed 7 packages: ['sng4onnx>=1.0.1', 'onnx_graphsurgeon>=0.3.26', 'onnx>=1.12.0', 'onnx2tf>1.17.5,<=1.22.3', 'onnxslim>=0.1.31', 'tflite_support', 'onnxruntime-gpu']\n",
"\u001b[31m\u001b[1mrequirements:\u001b[0m ⚠️ \u001b[1mRestart runtime or rerun command for updates to take effect\u001b[0m\n",
"\n",
"\n",
"\u001b[34m\u001b[1mTensorFlow SavedModel:\u001b[0m starting export with tensorflow 2.17.0...\n",
"Downloading https://github.com/ultralytics/assets/releases/download/v8.3.0/calibration_image_sample_data_20x128x128x3_float32.npy.zip to 'calibration_image_sample_data_20x128x128x3_float32.npy.zip'...\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"100%|██████████| 1.11M/1.11M [00:00<00:00, 120MB/s]\n",
"Unzipping calibration_image_sample_data_20x128x128x3_float32.npy.zip to /content/calibration_image_sample_data_20x128x128x3_float32.npy...: 100%|██████████| 1/1 [00:00<00:00, 34.45file/s]"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
"\u001b[34m\u001b[1mONNX:\u001b[0m starting export with onnx 1.17.0 opset 19...\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\u001b[34m\u001b[1mONNX:\u001b[0m slimming with onnxslim 0.1.39...\n",
"\u001b[34m\u001b[1mONNX:\u001b[0m export success ✅ 1.3s, saved as 'runs/detect/train/weights/best.onnx' (10.1 MB)\n",
"\u001b[34m\u001b[1mTensorFlow SavedModel:\u001b[0m starting TFLite export with onnx2tf 1.22.3...\n",
"\u001b[34m\u001b[1mTensorFlow SavedModel:\u001b[0m export success ✅ 51.8s, saved as 'runs/detect/train/weights/best_saved_model' (25.6 MB)\n",
"\n",
"\u001b[34m\u001b[1mTensorFlow Lite:\u001b[0m starting export with tensorflow 2.17.0...\n",
"\u001b[34m\u001b[1mTensorFlow Lite:\u001b[0m export success ✅ 0.0s, saved as 'runs/detect/train/weights/best_saved_model/best_float32.tflite' (10.1 MB)\n",
"\n",
"Export complete (53.3s)\n",
"Results saved to \u001b[1m/content/runs/detect/train/weights\u001b[0m\n",
"Predict: yolo predict task=detect model=runs/detect/train/weights/best_saved_model/best_float32.tflite imgsz=224 \n",
"Validate: yolo val task=detect model=runs/detect/train/weights/best_saved_model/best_float32.tflite imgsz=224 data=/usr/local/lib/python3.10/dist-packages/ultralytics/cfg/datasets/coco8.yaml \n",
"Visualize: https://netron.app\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"metrics = model.val()"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "Ywi3Pvg4YSTB",
"outputId": "a20fe976-afae-4a6a-f959-7fea8581c3d0"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Ultralytics 8.3.29 🚀 Python-3.10.12 torch-2.5.0+cu121 CUDA:0 (Tesla T4, 15102MiB)\n",
"YOLO11n summary (fused): 238 layers, 2,616,248 parameters, 0 gradients, 6.5 GFLOPs\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"\u001b[34m\u001b[1mval: \u001b[0mScanning /content/datasets/coco8/labels/val.cache... 4 images, 0 backgrounds, 0 corrupt: 100%|██████████| 4/4 [00:00