Full Code of Neuralearn/deep-learning-with-tensorflow-2 for AI

main 3dca0ac8c812 cached

83 files

20.4 MB

5.4M tokens

8 symbols

1 requests

Copy disabled (too large) Download .txt

Showing preview only (21,459K chars total). Download the full file to get everything.

Repository: Neuralearn/deep-learning-with-tensorflow-2
Branch: main
Commit: 3dca0ac8c812
Files: 83
Total size: 20.4 MB

Directory structure:
gitextract_a2eje9ii/

├── README.md
├── deep learning for computer vision/
│   ├── 1-Linear Regression for Predicting Price of second hand Cars by Neuralearn.ai-.ipynb
│   ├── 2-Malaria Detection by Neuralearn.ai-.ipynb
│   ├── 3-Malaria Detection by Neuralearn.ai [PyTorch Version]-.ipynb
│   ├── 4-Human Emotions Detection by Neuralearn.ai-.ipynb
│   ├── 5-YOLO Object Detection from Scratch by Neuralearn.ai-.ipynb
│   ├── 6-Image segmentation by Neuralearn.ai-.ipynb
│   ├── 7-People Counting by Neuralearn.ai-.ipynb
│   ├── 8-VAE by Neuralearn.ai-.ipynb
│   ├── 9-DCGAN By Neuralearn.ai-.ipynb
│   └── emotions-detection/
│       ├── Procfile
│       ├── locusts.py
│       ├── requirements.txt
│       ├── runtime.txt
│       └── service/
│           ├── __init__.py
│           ├── api/
│           │   ├── __init__.py
│           │   ├── api.py
│           │   └── endpoints/
│           │       ├── __init__.py
│           │       ├── detect.py
│           │       └── test.py
│           ├── core/
│           │   ├── __init__.py
│           │   ├── logic/
│           │   │   ├── __init__.py
│           │   │   └── onnx_inference.py
│           │   └── schemas/
│           │       ├── __init__.py
│           │       ├── input.py
│           │       └── output.py
│           └── main.py
├── deep learning for image generation/
│   ├── 1-VAE by Neuralearn.ai-.ipynb
│   ├── 2-DCGAN By Neuralearn.ai-.ipynb
│   ├── 3-WGAN By Neuralearn.ai-.ipynb
│   ├── 4-ProGAN by Neuralearn.ai-.ipynb
│   ├── 5-SRGAN By Neuralearn.ai-.ipynb
│   ├── 6-CycleGAN By Neuralearn.ai-.ipynb
│   └── 7-Diffusion Models Neuralearn.ai-.ipynb
├── deep learning for linear algebra/
│   └── Complete Linear Algebra Course by Neuralearn.ai-.ipynb
├── deep learning for natural language processing/
│   ├── 1-Linear Regression for Predicting Price of second hand Cars by Neuralearn.ai-.ipynb
│   ├── 10-Neural Machine Translation using HuggingFace 🤗 Transformers by Neuralearn.ai-.ipynb
│   ├── 11-Extractive Question Answering using HuggingFace 🤗 Transformers by Neuralearn.ai-.ipynb
│   ├── 12-Search Engine for e-commerce using Sentence Transformers in HuggingFace 🤗 by Neuralearn.ai-.ipynb
│   ├── 13-Lyrics Generator using GPT2 in HuggingFace 🤗 by Neuralearn.ai-.ipynb
│   ├── 14-Grammatical Error Correction using T5 in HuggingFace 🤗 by Neuralearn.ai-.ipynb
│   ├── 15-Chat With Elon Musk using BlenderBot in HuggingFace 🤗 Transformers by Neuralearn.ai-.ipynb
│   ├── 2-Sentiment Analysis with RNNs by Neuralearn.ai-.ipynb
│   ├── 3-Sentiment Analysis with Transformers by Neuralearn.ai-.ipynb
│   ├── 4-Neural Machine Translation with RNNs by Neuralearn.ai-.ipynb
│   ├── 5-Neural Machine Translation with Bahdanau Attention by Neuralearn.ai-.ipynb
│   ├── 6-Neural Machine Translation with Transformers by Neuralearn.ai-.ipynb
│   ├── 7-Sentiment Analysis with BERT in HuggingFace 🤗 by Neuralearn.ai-.ipynb
│   ├── 8-Intent Classification for Customer Service using HuggingFace 🤗 Transformers by Neuralearn.ai-.ipynb
│   └── 9-Named Entity Recognition using HuggingFace 🤗 Transformers by Neuralearn.ai-.ipynb
├── deep learning for object detection/
│   └── Deploying YoloX to Cloud by Neuralearn-.ipynb
├── deep learning for optical character recognition/
│   └── PDF TO EXCEL By Neuralearn-.ipynb
├── deprecated/
│   ├── .ipynb_checkpoints/
│   │   └── 21-dcgan_By_Neuralearn-checkpoint.ipynb
│   ├── 1-Linear Regression by Neuralearn.ai.ipynb
│   ├── 10-Breast Cancer detection by Neuralearn.ai.ipynb
│   ├── 11-YOLO by Neuralearn.ai.ipynb
│   ├── 12-YOLO v3 by Neuralearn.ai.ipynb
│   ├── 13-Semantic Segmentation by Neuralearn.ai.ipynb
│   ├── 14-People Counting by Neuralearn.ai.ipynb
│   ├── 15-Machine Translation with Sequence to Sequence Models by Neuralearn.ai.ipynb
│   ├── 16-Machine Translation with Attention Models by Neuralearn.ai.ipynb
│   ├── 17-Machine Translation with Transformers by Neuralearn.ai.ipynb
│   ├── 18-Question Answering by Neuralearn.ai.ipynb
│   ├── 19-Automatic Speech Recognition by Neuralearn.ai.ipynb
│   ├── 2-Logistic Regression by Neuralearn.ai.ipynb
│   ├── 20-Image Captioning by Neuralearn.ai.ipynb
│   ├── 21-dcgan_By_Neuralearn.ipynb
│   ├── 3-Softmax Regression by Neuralearn.ai.ipynb
│   ├── 4-Artificial Neural Networks from scratch Neuralearn.ai.ipynb
│   ├── 5-Lenet Model by Neuralearn.ai.ipynb
│   ├── 5-Transfer Learning by Neuralearn.ai.ipynb
│   ├── 6-Callbacks by Neuralearn.ai.ipynb
│   ├── 7-Transfer Learning and Finetuning by Neuralearn.ai.ipynb
│   ├── 8-Sentiment Analysis by Neuralearn.ai.ipynb
│   ├── 9-Word2Vec by Neuralearn.ai.ipynb
│   └── files/
│       ├── exam.csv
│       └── health.csv
└── neural networks from scratch/
    ├── 1-Linear Regression by Neuralearn.ai.ipynb
    ├── 2-Logistic Regression by Neuralearn.ai.ipynb
    ├── 3-Softmax Regression by Neuralearn.ai.ipynb
    ├── 4-Artificial Neural Networks from scratch Neuralearn.ai.ipynb
    └── files/
        ├── exam.csv
        └── health.csv

================================================
FILE CONTENTS
================================================

================================================
FILE: README.md
================================================
# deep-learning-with-tensorflow-2
Jupyter notebooks for Deep Learning with TensorFlow 2 Course


================================================
FILE: deep learning for computer vision/1-Linear Regression for Predicting Price of second hand Cars by Neuralearn.ai-.ipynb
================================================
{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"provenance":[{"file_id":"1MpOO7MxtkDaf3S0rIK8SDCfnpI6TmU_G","timestamp":1673816133355}],"collapsed_sections":["j6EtG3kpNKiT","CxlimoToLc4C","TSjCxq__LQkw"]},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"},"accelerator":"GPU"},"cells":[{"cell_type":"code","metadata":{"id":"Q_Wi6cQRp4Rv"},"source":["import tensorflow as tf### models\n","import pandas as pd ### reading and processing data\n","import seaborn as sns ### visualization\n","import numpy as np### math computations\n","import matplotlib.pyplot as plt### plotting bar chart\n","from tensorflow.keras.layers import Normalization, Dense, InputLayer\n","from tensorflow.keras.losses import MeanSquaredError, Huber, MeanAbsoluteError\n","from tensorflow.keras.metrics import RootMeanSquaredError\n","from tensorflow.keras.optimizers import Adam"],"execution_count":null,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"j6EtG3kpNKiT"},"source":["## **Data Preparation**"]},{"cell_type":"code","metadata":{"id":"_wKxrpeci_gT","colab":{"base_uri":"https://localhost:8080/","height":205},"executionInfo":{"status":"ok","timestamp":1635922384406,"user_tz":-60,"elapsed":19,"user":{"displayName":"martins folefac","photoUrl":"https://lh3.googleusercontent.com/a/default-user=s64","userId":"15114498789158493667"}},"outputId":"de7b09f9-1986-429b-f069-e27766c2c2fc"},"source":["data = pd.read_csv(\"train.csv\", \",\")\n","data.head()"],"execution_count":null,"outputs":[{"output_type":"execute_result","data":{"text/html":["<div>\n","<style scoped>\n","    .dataframe tbody tr th:only-of-type {\n","        vertical-align: middle;\n","    }\n","\n","    .dataframe tbody tr th {\n","        vertical-align: top;\n","    }\n","\n","    .dataframe thead th {\n","        text-align: right;\n","    }\n","</style>\n","<table border=\"1\" class=\"dataframe\">\n","  <thead>\n","    <tr style=\"text-align: right;\">\n","      <th></th>\n","      <th>v.id</th>\n","      <th>on road old</th>\n","      <th>on road now</th>\n","      <th>years</th>\n","      <th>km</th>\n","      <th>rating</th>\n","      <th>condition</th>\n","      <th>economy</th>\n","      <th>top speed</th>\n","      <th>hp</th>\n","      <th>torque</th>\n","      <th>current price</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>1</td>\n","      <td>535651</td>\n","      <td>798186</td>\n","      <td>3</td>\n","      <td>78945</td>\n","      <td>1</td>\n","      <td>2</td>\n","      <td>14</td>\n","      <td>177</td>\n","      <td>73</td>\n","      <td>123</td>\n","      <td>351318.0</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>2</td>\n","      <td>591911</td>\n","      <td>861056</td>\n","      <td>6</td>\n","      <td>117220</td>\n","      <td>5</td>\n","      <td>9</td>\n","      <td>9</td>\n","      <td>148</td>\n","      <td>74</td>\n","      <td>95</td>\n","      <td>285001.5</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>3</td>\n","      <td>686990</td>\n","      <td>770762</td>\n","      <td>2</td>\n","      <td>132538</td>\n","      <td>2</td>\n","      <td>8</td>\n","      <td>15</td>\n","      <td>181</td>\n","      <td>53</td>\n","      <td>97</td>\n","      <td>215386.0</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>4</td>\n","      <td>573999</td>\n","      <td>722381</td>\n","      <td>4</td>\n","      <td>101065</td>\n","      <td>4</td>\n","      <td>3</td>\n","      <td>11</td>\n","      <td>197</td>\n","      <td>54</td>\n","      <td>116</td>\n","      <td>244295.5</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>5</td>\n","      <td>691388</td>\n","      <td>811335</td>\n","      <td>6</td>\n","      <td>61559</td>\n","      <td>3</td>\n","      <td>9</td>\n","      <td>12</td>\n","      <td>160</td>\n","      <td>53</td>\n","      <td>105</td>\n","      <td>531114.5</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>"],"text/plain":["   v.id  on road old  on road now  years  ...  top speed  hp  torque  current price\n","0     1       535651       798186      3  ...        177  73     123       351318.0\n","1     2       591911       861056      6  ...        148  74      95       285001.5\n","2     3       686990       770762      2  ...        181  53      97       215386.0\n","3     4       573999       722381      4  ...        197  54     116       244295.5\n","4     5       691388       811335      6  ...        160  53     105       531114.5\n","\n","[5 rows x 12 columns]"]},"metadata":{},"execution_count":3}]},{"cell_type":"code","metadata":{"id":"txHuR6vUXK7-","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1635922384407,"user_tz":-60,"elapsed":16,"user":{"displayName":"martins folefac","photoUrl":"https://lh3.googleusercontent.com/a/default-user=s64","userId":"15114498789158493667"}},"outputId":"4f749ca2-75f0-4834-845e-eed50181660b"},"source":["data.shape"],"execution_count":null,"outputs":[{"output_type":"execute_result","data":{"text/plain":["(1000, 12)"]},"metadata":{},"execution_count":4}]},{"cell_type":"code","metadata":{"id":"U_l14YAjXLDD"},"source":["# data = pd.read_csv(\"train_semi.csv\", \",\")\n","# data.head()\n","# data.shape"],"execution_count":null,"outputs":[]},{"cell_type":"code","metadata":{"id":"Ssm3ewabXLFx","colab":{"base_uri":"https://localhost:8080/","height":999},"executionInfo":{"status":"ok","timestamp":1635922431466,"user_tz":-60,"elapsed":46423,"user":{"displayName":"martins folefac","photoUrl":"https://lh3.googleusercontent.com/a/default-user=s64","userId":"15114498789158493667"}},"outputId":"edfa5533-543d-4013-9b89-8a81de77b091"},"source":["sns.pairplot(data[['years', 'km', 'rating', 'condition', 'economy', 'top speed', 'hp', 'torque', 'current price']], diag_kind='kde')"],"execution_count":null,"outputs":[{"output_type":"execute_result","data":{"text/plain":["<seaborn.axisgrid.PairGrid at 0x7f9735927510>"]},"metadata":{},"execution_count":6},{"output_type":"display_data","data":{"image/png":"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

Download .txt

gitextract_a2eje9ii/

├── README.md
├── deep learning for computer vision/
│   ├── 1-Linear Regression for Predicting Price of second hand Cars by Neuralearn.ai-.ipynb
│   ├── 2-Malaria Detection by Neuralearn.ai-.ipynb
│   ├── 3-Malaria Detection by Neuralearn.ai [PyTorch Version]-.ipynb
│   ├── 4-Human Emotions Detection by Neuralearn.ai-.ipynb
│   ├── 5-YOLO Object Detection from Scratch by Neuralearn.ai-.ipynb
│   ├── 6-Image segmentation by Neuralearn.ai-.ipynb
│   ├── 7-People Counting by Neuralearn.ai-.ipynb
│   ├── 8-VAE by Neuralearn.ai-.ipynb
│   ├── 9-DCGAN By Neuralearn.ai-.ipynb
│   └── emotions-detection/
│       ├── Procfile
│       ├── locusts.py
│       ├── requirements.txt
│       ├── runtime.txt
│       └── service/
│           ├── __init__.py
│           ├── api/
│           │   ├── __init__.py
│           │   ├── api.py
│           │   └── endpoints/
│           │       ├── __init__.py
│           │       ├── detect.py
│           │       └── test.py
│           ├── core/
│           │   ├── __init__.py
│           │   ├── logic/
│           │   │   ├── __init__.py
│           │   │   └── onnx_inference.py
│           │   └── schemas/
│           │       ├── __init__.py
│           │       ├── input.py
│           │       └── output.py
│           └── main.py
├── deep learning for image generation/
│   ├── 1-VAE by Neuralearn.ai-.ipynb
│   ├── 2-DCGAN By Neuralearn.ai-.ipynb
│   ├── 3-WGAN By Neuralearn.ai-.ipynb
│   ├── 4-ProGAN by Neuralearn.ai-.ipynb
│   ├── 5-SRGAN By Neuralearn.ai-.ipynb
│   ├── 6-CycleGAN By Neuralearn.ai-.ipynb
│   └── 7-Diffusion Models Neuralearn.ai-.ipynb
├── deep learning for linear algebra/
│   └── Complete Linear Algebra Course by Neuralearn.ai-.ipynb
├── deep learning for natural language processing/
│   ├── 1-Linear Regression for Predicting Price of second hand Cars by Neuralearn.ai-.ipynb
│   ├── 10-Neural Machine Translation using HuggingFace 🤗 Transformers by Neuralearn.ai-.ipynb
│   ├── 11-Extractive Question Answering using HuggingFace 🤗 Transformers by Neuralearn.ai-.ipynb
│   ├── 12-Search Engine for e-commerce using Sentence Transformers in HuggingFace 🤗 by Neuralearn.ai-.ipynb
│   ├── 13-Lyrics Generator using GPT2 in HuggingFace 🤗 by Neuralearn.ai-.ipynb
│   ├── 14-Grammatical Error Correction using T5 in HuggingFace 🤗 by Neuralearn.ai-.ipynb
│   ├── 15-Chat With Elon Musk using BlenderBot in HuggingFace 🤗 Transformers by Neuralearn.ai-.ipynb
│   ├── 2-Sentiment Analysis with RNNs by Neuralearn.ai-.ipynb
│   ├── 3-Sentiment Analysis with Transformers by Neuralearn.ai-.ipynb
│   ├── 4-Neural Machine Translation with RNNs by Neuralearn.ai-.ipynb
│   ├── 5-Neural Machine Translation with Bahdanau Attention by Neuralearn.ai-.ipynb
│   ├── 6-Neural Machine Translation with Transformers by Neuralearn.ai-.ipynb
│   ├── 7-Sentiment Analysis with BERT in HuggingFace 🤗 by Neuralearn.ai-.ipynb
│   ├── 8-Intent Classification for Customer Service using HuggingFace 🤗 Transformers by Neuralearn.ai-.ipynb
│   └── 9-Named Entity Recognition using HuggingFace 🤗 Transformers by Neuralearn.ai-.ipynb
├── deep learning for object detection/
│   └── Deploying YoloX to Cloud by Neuralearn-.ipynb
├── deep learning for optical character recognition/
│   └── PDF TO EXCEL By Neuralearn-.ipynb
├── deprecated/
│   ├── .ipynb_checkpoints/
│   │   └── 21-dcgan_By_Neuralearn-checkpoint.ipynb
│   ├── 1-Linear Regression by Neuralearn.ai.ipynb
│   ├── 10-Breast Cancer detection by Neuralearn.ai.ipynb
│   ├── 11-YOLO by Neuralearn.ai.ipynb
│   ├── 12-YOLO v3 by Neuralearn.ai.ipynb
│   ├── 13-Semantic Segmentation by Neuralearn.ai.ipynb
│   ├── 14-People Counting by Neuralearn.ai.ipynb
│   ├── 15-Machine Translation with Sequence to Sequence Models by Neuralearn.ai.ipynb
│   ├── 16-Machine Translation with Attention Models by Neuralearn.ai.ipynb
│   ├── 17-Machine Translation with Transformers by Neuralearn.ai.ipynb
│   ├── 18-Question Answering by Neuralearn.ai.ipynb
│   ├── 19-Automatic Speech Recognition by Neuralearn.ai.ipynb
│   ├── 2-Logistic Regression by Neuralearn.ai.ipynb
│   ├── 20-Image Captioning by Neuralearn.ai.ipynb
│   ├── 21-dcgan_By_Neuralearn.ipynb
│   ├── 3-Softmax Regression by Neuralearn.ai.ipynb
│   ├── 4-Artificial Neural Networks from scratch Neuralearn.ai.ipynb
│   ├── 5-Lenet Model by Neuralearn.ai.ipynb
│   ├── 5-Transfer Learning by Neuralearn.ai.ipynb
│   ├── 6-Callbacks by Neuralearn.ai.ipynb
│   ├── 7-Transfer Learning and Finetuning by Neuralearn.ai.ipynb
│   ├── 8-Sentiment Analysis by Neuralearn.ai.ipynb
│   ├── 9-Word2Vec by Neuralearn.ai.ipynb
│   └── files/
│       ├── exam.csv
│       └── health.csv
└── neural networks from scratch/
    ├── 1-Linear Regression by Neuralearn.ai.ipynb
    ├── 2-Logistic Regression by Neuralearn.ai.ipynb
    ├── 3-Softmax Regression by Neuralearn.ai.ipynb
    ├── 4-Artificial Neural Networks from scratch Neuralearn.ai.ipynb
    └── files/
        ├── exam.csv
        └── health.csv

Download .txt

SYMBOL INDEX (8 symbols across 6 files)

FILE: deep learning for computer vision/emotions-detection/locusts.py
  class DetectorTask (line 3) | class DetectorTask(SequentialTaskSet):
    method detection (line 5) | def detection(self):
  class LoadTester (line 13) | class LoadTester(HttpUser):

FILE: deep learning for computer vision/emotions-detection/service/api/endpoints/detect.py
  function detect (line 10) | async def detect(im: UploadFile):

FILE: deep learning for computer vision/emotions-detection/service/api/endpoints/test.py
  function testing (line 6) | async def testing():

FILE: deep learning for computer vision/emotions-detection/service/core/logic/onnx_inference.py
  function emotions_detector (line 7) | def emotions_detector(img_array):

FILE: deep learning for computer vision/emotions-detection/service/core/schemas/output.py
  class APIOutput (line 3) | class APIOutput(BaseModel):

FILE: deep learning for computer vision/emotions-detection/service/main.py
  function root (line 15) | async def root():

Copy disabled (too large) Download .json

Condensed preview — 83 files, each showing path, character count, and a content snippet. Download the .json file for the full structured content (22,035K chars).

[
  {
    "path": "README.md",
    "chars": 95,
    "preview": "# deep-learning-with-tensorflow-2\nJupyter notebooks for Deep Learning with TensorFlow 2 Course\n"
  },
  {
    "path": "deep learning for computer vision/1-Linear Regression for Predicting Price of second hand Cars by Neuralearn.ai-.ipynb",
    "chars": 1521147,
    "preview": "{\"nbformat\":4,\"nbformat_minor\":0,\"metadata\":{\"colab\":{\"provenance\":[{\"file_id\":\"1MpOO7MxtkDaf3S0rIK8SDCfnpI6TmU_G\",\"time"
  },
  {
    "path": "deep learning for computer vision/2-Malaria Detection by Neuralearn.ai-.ipynb",
    "chars": 85410,
    "preview": "{\"cells\":[{\"cell_type\":\"code\",\"execution_count\":null,\"metadata\":{\"id\":\"rR4jSKq1m4WT\"},\"outputs\":[],\"source\":[\"import ten"
  },
  {
    "path": "deep learning for computer vision/3-Malaria Detection by Neuralearn.ai [PyTorch Version]-.ipynb",
    "chars": 589931,
    "preview": "{\"cells\":[{\"cell_type\":\"code\",\"execution_count\":null,\"metadata\":{\"id\":\"t7rPu5mRadux\"},\"outputs\":[],\"source\":[\"import num"
  },
  {
    "path": "deep learning for computer vision/4-Human Emotions Detection by Neuralearn.ai-.ipynb",
    "chars": 3982229,
    "preview": "{\"cells\":[{\"cell_type\":\"code\",\"execution_count\":null,\"metadata\":{\"id\":\"yIQNyieqUSN2\"},\"outputs\":[],\"source\":[\"import ten"
  },
  {
    "path": "deep learning for computer vision/5-YOLO Object Detection from Scratch by Neuralearn.ai-.ipynb",
    "chars": 616934,
    "preview": "{\"cells\":[{\"cell_type\":\"code\",\"execution_count\":null,\"metadata\":{\"id\":\"O9Jf4tDsfe1g\"},\"outputs\":[],\"source\":[\"import ten"
  },
  {
    "path": "deep learning for computer vision/6-Image segmentation by Neuralearn.ai-.ipynb",
    "chars": 8479,
    "preview": "{\"nbformat\":4,\"nbformat_minor\":0,\"metadata\":{\"colab\":{\"provenance\":[],\"authorship_tag\":\"ABX9TyPXRcvdfpG8Ah9S3v/Q6Z/3\"},\""
  },
  {
    "path": "deep learning for computer vision/7-People Counting by Neuralearn.ai-.ipynb",
    "chars": 9756,
    "preview": "{\"nbformat\":4,\"nbformat_minor\":0,\"metadata\":{\"colab\":{\"provenance\":[],\"authorship_tag\":\"ABX9TyOEYsHlbQ9MSIK58KUUGle3\"},\""
  },
  {
    "path": "deep learning for computer vision/8-VAE by Neuralearn.ai-.ipynb",
    "chars": 689937,
    "preview": "{\"nbformat\":4,\"nbformat_minor\":0,\"metadata\":{\"colab\":{\"provenance\":[{\"file_id\":\"14eFua9pLCV6AOYqGdyq_R-eWWUfZVtYs\",\"time"
  },
  {
    "path": "deep learning for computer vision/9-DCGAN By Neuralearn.ai-.ipynb",
    "chars": 524344,
    "preview": "{\"cells\":[{\"cell_type\":\"code\",\"execution_count\":null,\"metadata\":{\"id\":\"zGcCsOilc8b1\"},\"outputs\":[],\"source\":[\"import ten"
  },
  {
    "path": "deep learning for computer vision/emotions-detection/Procfile",
    "chars": 87,
    "preview": "web: gunicorn service.main:app --workers 2 --worker-class uvicorn.workers.UvicornWorker"
  },
  {
    "path": "deep learning for computer vision/emotions-detection/locusts.py",
    "chars": 402,
    "preview": "from locust import SequentialTaskSet, HttpUser, task\n\nclass DetectorTask(SequentialTaskSet):\n    @task\n    def detection"
  },
  {
    "path": "deep learning for computer vision/emotions-detection/requirements.txt",
    "chars": 705,
    "preview": "anyio==3.6.2\ncertifi==2022.9.24\nclick==8.1.3\ncoloredlogs==15.0.1\ndnspython==2.2.1\nemail-validator==1.3.0\nfastapi==0.87.0"
  },
  {
    "path": "deep learning for computer vision/emotions-detection/runtime.txt",
    "chars": 13,
    "preview": "python-3.9.15"
  },
  {
    "path": "deep learning for computer vision/emotions-detection/service/__init__.py",
    "chars": 0,
    "preview": ""
  },
  {
    "path": "deep learning for computer vision/emotions-detection/service/api/__init__.py",
    "chars": 0,
    "preview": ""
  },
  {
    "path": "deep learning for computer vision/emotions-detection/service/api/api.py",
    "chars": 239,
    "preview": "from fastapi import APIRouter\nfrom service.api.endpoints.detect import emo_router\nfrom service.api.endpoints.test import"
  },
  {
    "path": "deep learning for computer vision/emotions-detection/service/api/endpoints/__init__.py",
    "chars": 0,
    "preview": ""
  },
  {
    "path": "deep learning for computer vision/emotions-detection/service/api/endpoints/detect.py",
    "chars": 625,
    "preview": "from fastapi import APIRouter, UploadFile,HTTPException\nfrom PIL import Image\nfrom io import BytesIO\nimport numpy as np\n"
  },
  {
    "path": "deep learning for computer vision/emotions-detection/service/api/endpoints/test.py",
    "chars": 139,
    "preview": "from fastapi import APIRouter\n\ntest_router = APIRouter()\n\n@test_router.get(\"/test\")\nasync def testing():\n\n    return {\"t"
  },
  {
    "path": "deep learning for computer vision/emotions-detection/service/core/__init__.py",
    "chars": 0,
    "preview": ""
  },
  {
    "path": "deep learning for computer vision/emotions-detection/service/core/logic/__init__.py",
    "chars": 0,
    "preview": ""
  },
  {
    "path": "deep learning for computer vision/emotions-detection/service/core/logic/onnx_inference.py",
    "chars": 757,
    "preview": "import onnxruntime as rt\nimport cv2\nimport numpy as np\nimport time\nimport service.main as s\n\ndef emotions_detector(img_a"
  },
  {
    "path": "deep learning for computer vision/emotions-detection/service/core/schemas/__init__.py",
    "chars": 0,
    "preview": ""
  },
  {
    "path": "deep learning for computer vision/emotions-detection/service/core/schemas/input.py",
    "chars": 0,
    "preview": ""
  },
  {
    "path": "deep learning for computer vision/emotions-detection/service/core/schemas/output.py",
    "chars": 98,
    "preview": "from pydantic import BaseModel\n\nclass APIOutput(BaseModel):\n    emotion: str\n    time_elapsed: str"
  },
  {
    "path": "deep learning for computer vision/emotions-detection/service/main.py",
    "chars": 364,
    "preview": "from fastapi import FastAPI\nfrom service.api.api import main_router\nimport onnxruntime as rt\n\napp = FastAPI(project_name"
  },
  {
    "path": "deep learning for image generation/1-VAE by Neuralearn.ai-.ipynb",
    "chars": 689937,
    "preview": "{\"nbformat\":4,\"nbformat_minor\":0,\"metadata\":{\"colab\":{\"provenance\":[{\"file_id\":\"14eFua9pLCV6AOYqGdyq_R-eWWUfZVtYs\",\"time"
  },
  {
    "path": "deep learning for image generation/2-DCGAN By Neuralearn.ai-.ipynb",
    "chars": 524344,
    "preview": "{\"cells\":[{\"cell_type\":\"code\",\"execution_count\":null,\"metadata\":{\"id\":\"zGcCsOilc8b1\"},\"outputs\":[],\"source\":[\"import ten"
  },
  {
    "path": "deep learning for image generation/3-WGAN By Neuralearn.ai-.ipynb",
    "chars": 512214,
    "preview": "{\"cells\":[{\"cell_type\":\"code\",\"execution_count\":null,\"metadata\":{\"id\":\"zGcCsOilc8b1\"},\"outputs\":[],\"source\":[\"import ten"
  },
  {
    "path": "deep learning for image generation/4-ProGAN by Neuralearn.ai-.ipynb",
    "chars": 1554440,
    "preview": "{\"cells\":[{\"cell_type\":\"code\",\"execution_count\":null,\"metadata\":{\"colab\":{\"base_uri\":\"https://localhost:8080/\"},\"executi"
  },
  {
    "path": "deep learning for image generation/5-SRGAN By Neuralearn.ai-.ipynb",
    "chars": 484817,
    "preview": "{\"cells\":[{\"cell_type\":\"code\",\"execution_count\":null,\"metadata\":{\"id\":\"zGcCsOilc8b1\"},\"outputs\":[],\"source\":[\"import ten"
  },
  {
    "path": "deep learning for image generation/6-CycleGAN By Neuralearn.ai-.ipynb",
    "chars": 660471,
    "preview": "{\"cells\":[{\"cell_type\":\"code\",\"source\":[\"!pip install tensorflow-addons\"],\"metadata\":{\"colab\":{\"base_uri\":\"https://local"
  },
  {
    "path": "deep learning for image generation/7-Diffusion Models Neuralearn.ai-.ipynb",
    "chars": 1600391,
    "preview": "{\"cells\":[{\"cell_type\":\"code\",\"execution_count\":null,\"metadata\":{\"colab\":{\"base_uri\":\"https://localhost:8080/\"},\"executi"
  },
  {
    "path": "deep learning for linear algebra/Complete Linear Algebra Course by Neuralearn.ai-.ipynb",
    "chars": 61765,
    "preview": "{\"nbformat\":4,\"nbformat_minor\":0,\"metadata\":{\"colab\":{\"provenance\":[{\"file_id\":\"1Q6D2k0URW3Vl4SolHcAgR49NZtoq38o8\",\"time"
  },
  {
    "path": "deep learning for natural language processing/1-Linear Regression for Predicting Price of second hand Cars by Neuralearn.ai-.ipynb",
    "chars": 1521147,
    "preview": "{\"nbformat\":4,\"nbformat_minor\":0,\"metadata\":{\"colab\":{\"provenance\":[{\"file_id\":\"1MpOO7MxtkDaf3S0rIK8SDCfnpI6TmU_G\",\"time"
  },
  {
    "path": "deep learning for natural language processing/10-Neural Machine Translation using HuggingFace 🤗 Transformers by Neuralearn.ai-.ipynb",
    "chars": 135866,
    "preview": "{\"cells\":[{\"cell_type\":\"markdown\",\"metadata\":{\"id\":\"gwDUFKDdR6i_\"},\"source\":[\"# Installation\"]},{\"cell_type\":\"code\",\"exe"
  },
  {
    "path": "deep learning for natural language processing/11-Extractive Question Answering using HuggingFace 🤗 Transformers by Neuralearn.ai-.ipynb",
    "chars": 558865,
    "preview": "{\"cells\":[{\"cell_type\":\"markdown\",\"metadata\":{\"id\":\"gwDUFKDdR6i_\"},\"source\":[\"# Installation\"]},{\"cell_type\":\"code\",\"sou"
  },
  {
    "path": "deep learning for natural language processing/12-Search Engine for e-commerce using Sentence Transformers in HuggingFace 🤗 by Neuralearn.ai-.ipynb",
    "chars": 197964,
    "preview": "{\"cells\":[{\"cell_type\":\"markdown\",\"metadata\":{\"id\":\"-iNHt6FDdniF\"},\"source\":[\"# Installations and Imports\"]},{\"cell_type"
  },
  {
    "path": "deep learning for natural language processing/13-Lyrics Generator using GPT2 in HuggingFace 🤗 by Neuralearn.ai-.ipynb",
    "chars": 209265,
    "preview": "{\"nbformat\":4,\"nbformat_minor\":0,\"metadata\":{\"colab\":{\"provenance\":[{\"file_id\":\"11b7G2ndGk73SXvu8Wx5sdW44UH8WhrMa\",\"time"
  },
  {
    "path": "deep learning for natural language processing/14-Grammatical Error Correction using T5 in HuggingFace 🤗 by Neuralearn.ai-.ipynb",
    "chars": 250233,
    "preview": "{\"nbformat\":4,\"nbformat_minor\":0,\"metadata\":{\"colab\":{\"provenance\":[{\"file_id\":\"1KvHEKSeRWHa4b85ZMwl4BabG1r3Yo6_j\",\"time"
  },
  {
    "path": "deep learning for natural language processing/15-Chat With Elon Musk using BlenderBot in HuggingFace 🤗 Transformers by Neuralearn.ai-.ipynb",
    "chars": 192167,
    "preview": "{\"cells\":[{\"cell_type\":\"markdown\",\"metadata\":{\"id\":\"gwDUFKDdR6i_\"},\"source\":[\"# Installation\"]},{\"cell_type\":\"code\",\"exe"
  },
  {
    "path": "deep learning for natural language processing/2-Sentiment Analysis with RNNs by Neuralearn.ai-.ipynb",
    "chars": 306338,
    "preview": "{\"nbformat\":4,\"nbformat_minor\":0,\"metadata\":{\"colab\":{\"provenance\":[{\"file_id\":\"1ekGLJqUm4hoXzVs3h2I_OfnSCNwm1p8j\",\"time"
  },
  {
    "path": "deep learning for natural language processing/3-Sentiment Analysis with Transformers by Neuralearn.ai-.ipynb",
    "chars": 143126,
    "preview": "{\"nbformat\":4,\"nbformat_minor\":0,\"metadata\":{\"colab\":{\"provenance\":[{\"file_id\":\"1qG67bWTlIgR_WzHRVCiw1CicPYSTv4qn\",\"time"
  },
  {
    "path": "deep learning for natural language processing/4-Neural Machine Translation with RNNs by Neuralearn.ai-.ipynb",
    "chars": 491848,
    "preview": "{\"nbformat\":4,\"nbformat_minor\":0,\"metadata\":{\"colab\":{\"provenance\":[{\"file_id\":\"1wOi9I4Ett5qIJ3eldJ3bTPRmUjk3X5hd\",\"time"
  },
  {
    "path": "deep learning for natural language processing/5-Neural Machine Translation with Bahdanau Attention by Neuralearn.ai-.ipynb",
    "chars": 52944,
    "preview": "{\"nbformat\":4,\"nbformat_minor\":0,\"metadata\":{\"colab\":{\"provenance\":[{\"file_id\":\"1Azfk7PQQ3FoBJWSxSkqxquML6LYpZCYS\",\"time"
  },
  {
    "path": "deep learning for natural language processing/6-Neural Machine Translation with Transformers by Neuralearn.ai-.ipynb",
    "chars": 131114,
    "preview": "{\"cells\":[{\"cell_type\":\"code\",\"execution_count\":null,\"metadata\":{\"id\":\"5eMMJssyxQ-J\"},\"outputs\":[],\"source\":[\"#!pip inst"
  },
  {
    "path": "deep learning for natural language processing/7-Sentiment Analysis with BERT in HuggingFace 🤗 by Neuralearn.ai-.ipynb",
    "chars": 251661,
    "preview": "{\"cells\":[{\"cell_type\":\"markdown\",\"metadata\":{\"id\":\"gwDUFKDdR6i_\"},\"source\":[\"# Installation\"]},{\"cell_type\":\"code\",\"exe"
  },
  {
    "path": "deep learning for natural language processing/8-Intent Classification for Customer Service using HuggingFace 🤗 Transformers by Neuralearn.ai-.ipynb",
    "chars": 1432057,
    "preview": "{\"cells\":[{\"cell_type\":\"markdown\",\"metadata\":{\"id\":\"gwDUFKDdR6i_\"},\"source\":[\"# Installation\"]},{\"cell_type\":\"code\",\"exe"
  },
  {
    "path": "deep learning for natural language processing/9-Named Entity Recognition using HuggingFace 🤗 Transformers by Neuralearn.ai-.ipynb",
    "chars": 982684,
    "preview": "{\"cells\":[{\"cell_type\":\"markdown\",\"metadata\":{\"id\":\"gwDUFKDdR6i_\"},\"source\":[\"# Installation\"]},{\"cell_type\":\"code\",\"exe"
  },
  {
    "path": "deep learning for object detection/Deploying YoloX to Cloud by Neuralearn-.ipynb",
    "chars": 54479,
    "preview": "{\"nbformat\":4,\"nbformat_minor\":0,\"metadata\":{\"colab\":{\"provenance\":[{\"file_id\":\"1VQXsMZKl1z0CfLRIFAsJfXb0uOh6j3w-\",\"time"
  },
  {
    "path": "deep learning for optical character recognition/PDF TO EXCEL By Neuralearn-.ipynb",
    "chars": 60046,
    "preview": "{\"cells\":[{\"cell_type\":\"code\",\"source\":[\"from PIL import Image\\n\",\"import cv2\\n\",\"import numpy as np\\n\",\"import pandas a"
  },
  {
    "path": "deprecated/.ipynb_checkpoints/21-dcgan_By_Neuralearn-checkpoint.ipynb",
    "chars": 10538,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"execution_count\": null,\n   \"id\": \"1ebd04ae\",\n   \"metadata\": {},\n   \"output"
  },
  {
    "path": "deprecated/1-Linear Regression by Neuralearn.ai.ipynb",
    "chars": 4163,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"execution_count\": 1,\n   \"id\": \"92c53c20\",\n   \"metadata\": {},\n   \"outputs\":"
  },
  {
    "path": "deprecated/10-Breast Cancer detection by Neuralearn.ai.ipynb",
    "chars": 12234,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"execution_count\": null,\n   \"id\": \"e105f643\",\n   \"metadata\": {},\n   \"output"
  },
  {
    "path": "deprecated/11-YOLO by Neuralearn.ai.ipynb",
    "chars": 23754,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"execution_count\": null,\n   \"id\": \"e105f643\",\n   \"metadata\": {},\n   \"output"
  },
  {
    "path": "deprecated/12-YOLO v3 by Neuralearn.ai.ipynb",
    "chars": 28781,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"execution_count\": null,\n   \"id\": \"e105f643\",\n   \"metadata\": {},\n   \"output"
  },
  {
    "path": "deprecated/13-Semantic Segmentation by Neuralearn.ai.ipynb",
    "chars": 10653,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"execution_count\": null,\n   \"id\": \"e105f643\",\n   \"metadata\": {},\n   \"output"
  },
  {
    "path": "deprecated/14-People Counting by Neuralearn.ai.ipynb",
    "chars": 11895,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"execution_count\": null,\n   \"id\": \"e105f643\",\n   \"metadata\": {},\n   \"output"
  },
  {
    "path": "deprecated/15-Machine Translation with Sequence to Sequence Models by Neuralearn.ai.ipynb",
    "chars": 13341,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"execution_count\": null,\n   \"id\": \"ae647638\",\n   \"metadata\": {},\n   \"output"
  },
  {
    "path": "deprecated/16-Machine Translation with Attention Models by Neuralearn.ai.ipynb",
    "chars": 15501,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"execution_count\": null,\n   \"id\": \"e105f643\",\n   \"metadata\": {},\n   \"output"
  },
  {
    "path": "deprecated/17-Machine Translation with Transformers by Neuralearn.ai.ipynb",
    "chars": 22939,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"execution_count\": null,\n   \"id\": \"e105f643\",\n   \"metadata\": {},\n   \"output"
  },
  {
    "path": "deprecated/18-Question Answering by Neuralearn.ai.ipynb",
    "chars": 23506,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"execution_count\": null,\n   \"id\": \"e105f643\",\n   \"metadata\": {},\n   \"output"
  },
  {
    "path": "deprecated/19-Automatic Speech Recognition by Neuralearn.ai.ipynb",
    "chars": 10324,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"execution_count\": null,\n   \"id\": \"e105f643\",\n   \"metadata\": {},\n   \"output"
  },
  {
    "path": "deprecated/2-Logistic Regression by Neuralearn.ai.ipynb",
    "chars": 4891,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"execution_count\": 4,\n   \"id\": \"3ffc022e\",\n   \"metadata\": {},\n   \"outputs\":"
  },
  {
    "path": "deprecated/20-Image Captioning by Neuralearn.ai.ipynb",
    "chars": 17272,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"execution_count\": null,\n   \"id\": \"e105f643\",\n   \"metadata\": {},\n   \"output"
  },
  {
    "path": "deprecated/21-dcgan_By_Neuralearn.ipynb",
    "chars": 12453,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"execution_count\": null,\n   \"id\": \"1ebd04ae\",\n   \"metadata\": {},\n   \"output"
  },
  {
    "path": "deprecated/3-Softmax Regression by Neuralearn.ai.ipynb",
    "chars": 4933,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"execution_count\": null,\n   \"id\": \"f46cab9c\",\n   \"metadata\": {},\n   \"output"
  },
  {
    "path": "deprecated/4-Artificial Neural Networks from scratch Neuralearn.ai.ipynb",
    "chars": 10210,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"execution_count\": null,\n   \"id\": \"3014de4e\",\n   \"metadata\": {},\n   \"output"
  },
  {
    "path": "deprecated/5-Lenet Model by Neuralearn.ai.ipynb",
    "chars": 4248,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"execution_count\": null,\n   \"id\": \"4d8e0693\",\n   \"metadata\": {},\n   \"output"
  },
  {
    "path": "deprecated/5-Transfer Learning by Neuralearn.ai.ipynb",
    "chars": 7349,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"execution_count\": null,\n   \"id\": \"4d8e0693\",\n   \"metadata\": {},\n   \"output"
  },
  {
    "path": "deprecated/6-Callbacks by Neuralearn.ai.ipynb",
    "chars": 10089,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"execution_count\": null,\n   \"id\": \"9f15758c\",\n   \"metadata\": {},\n   \"output"
  },
  {
    "path": "deprecated/7-Transfer Learning and Finetuning by Neuralearn.ai.ipynb",
    "chars": 7782,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"execution_count\": null,\n   \"id\": \"9f15758c\",\n   \"metadata\": {},\n   \"output"
  },
  {
    "path": "deprecated/8-Sentiment Analysis by Neuralearn.ai.ipynb",
    "chars": 10866,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"execution_count\": null,\n   \"id\": \"f9cb825c\",\n   \"metadata\": {},\n   \"output"
  },
  {
    "path": "deprecated/9-Word2Vec by Neuralearn.ai.ipynb",
    "chars": 10713,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"execution_count\": null,\n   \"id\": \"223e425c\",\n   \"metadata\": {},\n   \"output"
  },
  {
    "path": "deprecated/files/exam.csv",
    "chars": 400,
    "preview": "EXAM1,EXAM2,EXAM3,FINAL,\n73,80,75,152,0\n93,88,93,185,1\n89,91,90,180,1\n96,98,100,196,1\n73,66,70,142,0\n53,46,55,101,0\n69,7"
  },
  {
    "path": "deprecated/files/health.csv",
    "chars": 1672,
    "preview": "X1,X2,X3,X4,X5\n8,78,284,9.10000038,109\n9.30000019,68,433,8.69999981,144\n7.5,70,739,7.19999981,113\n8.89999962,96,1792,8.8"
  },
  {
    "path": "neural networks from scratch/1-Linear Regression by Neuralearn.ai.ipynb",
    "chars": 4163,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"execution_count\": 1,\n   \"id\": \"92c53c20\",\n   \"metadata\": {},\n   \"outputs\":"
  },
  {
    "path": "neural networks from scratch/2-Logistic Regression by Neuralearn.ai.ipynb",
    "chars": 4891,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"execution_count\": 4,\n   \"id\": \"3ffc022e\",\n   \"metadata\": {},\n   \"outputs\":"
  },
  {
    "path": "neural networks from scratch/3-Softmax Regression by Neuralearn.ai.ipynb",
    "chars": 4933,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"execution_count\": null,\n   \"id\": \"f46cab9c\",\n   \"metadata\": {},\n   \"output"
  },
  {
    "path": "neural networks from scratch/4-Artificial Neural Networks from scratch Neuralearn.ai.ipynb",
    "chars": 10210,
    "preview": "{\n \"cells\": [\n  {\n   \"cell_type\": \"code\",\n   \"execution_count\": null,\n   \"id\": \"3014de4e\",\n   \"metadata\": {},\n   \"output"
  },
  {
    "path": "neural networks from scratch/files/exam.csv",
    "chars": 400,
    "preview": "EXAM1,EXAM2,EXAM3,FINAL,\n73,80,75,152,0\n93,88,93,185,1\n89,91,90,180,1\n96,98,100,196,1\n73,66,70,142,0\n53,46,55,101,0\n69,7"
  },
  {
    "path": "neural networks from scratch/files/health.csv",
    "chars": 1672,
    "preview": "X1,X2,X3,X4,X5\n8,78,284,9.10000038,109\n9.30000019,68,433,8.69999981,144\n7.5,70,739,7.19999981,113\n8.89999962,96,1792,8.8"
  }
]

About this extraction

This page contains the full source code of the Neuralearn/deep-learning-with-tensorflow-2 GitHub repository, extracted and formatted as plain text for AI agents and large language models (LLMs). The extraction includes 83 files (20.4 MB), approximately 5.4M tokens, and a symbol index with 8 extracted functions, classes, methods, constants, and types. Use this with OpenClaw, Claude, ChatGPT, Cursor, Windsurf, or any other AI tool that accepts text input. You can copy the full output to your clipboard or download it as a .txt file.

Extracted by GitExtract — free GitHub repo to text converter for AI. Built by Nikandr Surkov.

Extract another repo