Showing preview only (4,127K chars total). Download the full file or copy to clipboard to get everything.
Repository: dasoto/skincancer
Branch: master
Commit: 7265f1fe8c8d
Files: 24
Total size: 3.9 MB
Directory structure:
gitextract_zm89e7wg/
├── Project_Proposal.md
├── README.md
├── _config.yml
├── models/
│ ├── Model1-CNNScratch.mlmodel
│ ├── Model1.mlmodel
│ └── mymodel-2.h5
├── notebooks/
│ └── CNN Layers Visualization.ipynb
└── src/
├── app.py
├── cnn_model.py
├── image_preparation.py
├── iphone_model.py
├── moleimages.py
├── templates/
│ ├── index.html
│ ├── predict.html
│ ├── predict_old.html
│ └── upload.html
├── test_model.py
├── top_vgg.py
├── train_model.new.py
├── train_model.py
├── train_model_DA.py
├── train_model_VGG_full.py
├── train_model_VGG_full_DA.py
└── train_model_VGG_top.py
================================================
FILE CONTENTS
================================================
================================================
FILE: Project_Proposal.md
================================================
# Capstone Project Proposal
#### *by David Soto* - dasoto@gmail.com
@Galvanize Data Science Immersive Program
## CNN to identify malign moles on skin
### 1. Project Summary and motivation
The purpose of this project is to create a tool that considering the image of a
mole, can calculate the probability that a mole can be malign.
Skin cancer is a common disease that affect a big amount of
peoples. Some facts about skin cancer:
- Every year there are more new cases of skin cancer than the
combined incidence of cancers of the breast, prostate, lung and colon.
- An estimated 87,110 new cases of invasive melanoma will be diagnosed in the U.S.
in 2017.
- The estimated 5-year survival rate for patients whose melanoma is detected
early is about 98 percent in the U.S. The survival rate falls to 62 percent when
the disease reaches the lymph nodes, and 18 percent when the disease metastasizes
to distant organs.
### 2. Development process and Data
The idea of this project is to construct a CNN model that can predict the probability
that a specific mole can be malign.
#### 2.1 Data:
To train this model I'm planning to use
a set of images from the International Skin Imaging Collaboration: Mellanoma
Project ISIC https://isic-archive.com.
The specific datasets to use are:
- ISIC_UDA-2_1: Moles and melanomas. Biopsy-confirmed melanocytic lesions. Both malignant and benign lesions are included.
- Benign: 23
- Malign: 37
- ISIC_UDA-1_1 Moles and melanomas. Biopsy-confirmed melanocytic lesions. Both malignant and benign lesions are included.
- Benign: 398
- Malign: 159
- ISIC_MSK-2_1: Benign and malignant skin lesions. Biopsy-confirmed melanocytic and non-melanocytic lesions.
- Benign: 1167 (Not used)
- Malign: 352
- ISIC_MSK-1_2: Both malignant and benign melanocytic and non-melanocytic lesions. Almost all images confirmed by histopathology. Images not taken with modern digital cameras.
- Benign: 339
- Malign: 77
- ISIC_MSK-1_1: Moles and melanomas. Biopsy-confirmed melanocytic lesions, both malignant and benign.
- Benign: 448
- Malign: 224
As summary the total images to use are:
| Benign Images | Malign Images |
| :------------- | :------------- |
| 1208 | 849 |
Some sample images are shown below:
1. Sample images of benign moles:

- Sample images of malign moles:

#### 2.2 Preprocessing:
The following preprocessing tasks are going to be developed for each image:
1. Visual inspection to detect images with low quality or not representative
2. Image resizing: Transform images to 128x128x3
3. Crop images: Automatic or manual Crop
4. Other to define later in order to improve model quality
#### 2.3 CNN Model:
The idea is to develop a simple CNN model from scratch, and evaluate the performance
to set a baseline. The following steps to improve the model are:
1. Data augmentation: Rotations, noising, scaling to avoid overfitting
2. Transferred Learning: Using a pre-trained network construct some additional
layer at the end to fine tuning our model. (VGG-16, or other)
3. Others to define.
#### 2.4 Model Evaluation:
To evaluate the different models we will use ROC Curves and AUC score. To choose
the correct model we will evaluate the precision and accuracy to set the threshold
level that represent a good tradeoff between TPR and FPR.
### 3. Results presentation
As mention before the idea is to generate a tool to predict the probability of a
malign mole. To do it, I'm planning to provide the following resources:
**1. Web App:** The web app will have the possibility that a user upload a high
quality image of an specific mole. The results will be a prediction about the
probability that the given mole be malign in terms of percentage. The backend
that contain the web app and model loaded will be located in Amazon Web Services.
**2. Iphone App:** Our CNN model will be loaded into the iPhone to make local predictions.
Advantages: The image data don't need to be uploaded to any server, because the
model predictions can be done through the pre-trained model loaded into the iPhone.
**3. Android App:** (Optional if time allow it)
### 4. Project Schedule
| Activity | Days | Current Status | Progress |
| :------------- | :------------- | :------------- | :-------------|
| 1. Data Acquisition | 1 | Done | ++++|
| 2. Initial Preprocessing and visualizations | 1| Done | ++++|
| 3. First Model Construction and tuning | 2 | Done | ++++|
| 4. Model Optimization I (Data augmentation) | 1 | Pending| ----|
| 5. Model Optimization II (Transferred learning) | 2 | Pending| ----|
| 6. Model Optimization III (Fine Tuning)| 2| Pending| ----|
| 7. Web App Development + Backend Service | 2 | Pending| ----|
| 8. Ios App Development | 2| In Progress| ++--|
| 9. Android App Development | 2| Pending| ----|
| 10. Presentation preparation | 1 | Pending| ----|
### 5. Tools to Use
- Tensorflow (GPU High performance computing - NVIDIA)
- keras
- Python
- matplotlib
- scikit-learn
- AWS (EC2 - S3)
- IoS swift + core ML
- Flask
### 6. Current Progress
#### First Model: CNN from scratch, no data augmentation
Simple Convolutional Neural Network with 3 layers.
The results obtained until now can be shown on the ROC curve presented below:

### 7. Next Steps
TBD
================================================
FILE: README.md
================================================
# CNN to identify malign moles on skin
#### *by David Soto* - dasoto@gmail.com
@Galvanize Data Science Immersive Program
### 1. Project Summary and motivation
The purpose of this project is to create a tool that considering the image of a
mole, can calculate the probability that a mole can be malign.
Skin cancer is a common disease that affect a big amount of
peoples. Some facts about skin cancer:
- Every year there are more new cases of skin cancer than the
combined incidence of cancers of the breast, prostate, lung and colon.
- An estimated 87,110 new cases of invasive melanoma will be diagnosed in the U.S.
in 2017.
- The estimated 5-year survival rate for patients whose melanoma is detected
early is about 98 percent in the U.S. The survival rate falls to 62 percent when
the disease reaches the lymph nodes, and 18 percent when the disease metastasizes
to distant organs.
- Early detection is critical!
### 2. Development process and Data
The idea of this project is to construct a CNN model that can predict the probability
that a specific mole can be malign.
#### 2.1 Data:
To train this model the data to use is a set of images from the International
Skin Imaging Collaboration: Mellanoma Project ISIC https://isic-archive.com.
The specific datasets to use are:
- ISIC_UDA-2_1: Moles and melanomas. Biopsy-confirmed melanocytic lesions. Both malignant and benign lesions are included.
- Benign: 23
- Malign: 37
- ISIC_UDA-1_1 Moles and melanomas. Biopsy-confirmed melanocytic lesions. Both malignant and benign lesions are included.
- Benign: 398
- Malign: 159
- ISIC_MSK-2_1: Benign and malignant skin lesions. Biopsy-confirmed melanocytic and non-melanocytic lesions.
- Benign: 1167 (Not used)
- Malign: 352
- ISIC_MSK-1_2: Both malignant and benign melanocytic and non-melanocytic lesions. Almost all images confirmed by histopathology. Images not taken with modern digital cameras.
- Benign: 339
- Malign: 77
- ISIC_MSK-1_1: Moles and melanomas. Biopsy-confirmed melanocytic lesions, both malignant and benign.
- Benign: 448
- Malign: 224
As summary the total images to use are:
| Benign Images | Malignant Images |
| :------------- | :-----------------|
| 1208 | 849 |
Some sample images are shown below:
1. Sample images of benign moles:

- Sample images of malign moles:

#### 2.2 Preprocessing:
The following preprocessing tasks are developed for each image:
1. Visual inspection to detect images with low quality or not representative
2. Image resizing: Transform images to 128x128x3
3. Crop images: Automatic or manual Crop
4. Other to define later in order to improve model quality
#### 2.3 CNN Model:
The idea is to develop a simple CNN model from scratch, and evaluate the performance to set a baseline. The following steps to improve the model are:
1. Data augmentation: Rotations, noising, scaling to avoid overfitting
2. Transferred Learning: Using a pre-trained network construct some additional
layer at the end to fine tuning our model. (VGG-16, or other)
3. Full training of VGG-16 + additional layer.
#### 2.4 Model Evaluation:
To evaluate the different models we will use ROC Curves and AUC score. To choose
the correct model we will evaluate the precision and accuracy to set the threshold
level that represent a good tradeoff between TPR and FPR.
### 3. Results presentation
As mention before the idea is to generate a tool to predict the probability of a
malign mole. To do it, I'm planning to provide the following resources:
**1. Web App:** The web app will have the possibility that a user upload a high
quality image of an specific mole. The results will be a prediction about the
probability that the given mole be malign in terms of percentage. The backend
that contain the web app and model loaded will be located in Amazon Web Services.
**2. Iphone App:** Our CNN model will be loaded into the iPhone to make local predictions.
Advantages: The image data don't need to be uploaded to any server, because the
model predictions can be done through the pre-trained model loaded into the iPhone.
**3. Android App:** (Optional if time allow it)
### 4. Project Schedule
| Activity | Days | Status | Prog |
| :---------------------------------------------- | :--- | :---------- | :--- |
| 1. Data Acquisition | 1 | Done | ++++ |
| 2. Initial Preprocessing and visualizations | 1 | Done | ++++ |
| 3. First Model Construction and tuning | 2 | Done | ++++ |
| 4. Model Optimization I (Data augmentation) | 1 | Done | ++++ |
| 5. Model Optimization II (Transferred learning) | 2 | Done | ++++ |
| 6. Model Optimization III (Fine Tuning) | 2 | Done | ++++ |
| 7. Web App Development + Backend Service | 2 | Done | ++++ |
| 8. Ios App Development | 2 | Done | ++++ |
| 9. Android App Development | 2 | Pending | ---- |
| 10. Presentation preparation | 1 | Done | ++++ |
### 5. Tools to Use
- Tensorflow (GPU High performance computing - NVIDIA)
- keras
- Python
- matplotlib
- scikit-learn
- AWS (EC2 - S3)
- IoS swift + core ML
- Flask

### 6. Final Results
#### First Model: CNN from scratch, no data augmentation
Simple Convolutional Neural Network with 3 layers.
The results obtained until now can be shown on the ROC curve presented below:

##### Classification Report CNN From scratch, CV Folder.
- Model_name = models/cnn-scratch-cv.hdf5
- 110 epochs. No early stop.
- AUC: 0.9164
| class | precision | recall | f1-score | support
| :------------- | :------------- | :------------- | :-------------| :------------|
|0.0 | 0.86 | 0.88 | 0.87 | 50|
|1.0 | 0.88 | 0.86 | 0.87 | 50 |
| avg / total | 0.87 | 0.87 | 0.87 | 100|
#### Second Model: VGG16 + Dense Layer
##### Classification Report VGG16 + Dense Layer.
- Model_name = models/VGG-Full.hdf5
- 100 epochs. No early stop.
- AUC: 0.9496
|class |precision | recall | f1-score | support |
| :-------- | :------ | :----- | :---- | :---- |
|0.0 | 0.87 | 0.92 | 0.89 | 50 |
|1.0 | 0.91 | 0.86 | 0.89 | 50 |
|avg / total | 0.89 | 0.89 | 0.89 | 100 |
##### Classification Report VGG16 + Dense Layer.
- Model_name = models/BM_VA_VGG_FULL_2.hdf5
- 100 epochs.ModelCheckpoint. Best Val Accuracy
- AUC: 0.93
|class |precision | recall |f1-score | support|
|:-----|:-----------|:--------|:---------|:-------|
|0.0 | 0.82 |0.94 |0.88 | 50 |
|1.0 | 0.93 | 0.80 | 0.86 | 50 |
|avg / total| 0.88 | 0.87 | 0.87| 100 |
#### Third Model: CNN + Data Augmentation
##### Classification Report CNN Scratch with Data Augmentation.
- Model_name = models/CNN-Scratch-DA
- 100 epochs.ModelCheckpoint. Best Val Accuracy
- AUC: 0.9444
| class | precision | recall | f1-score | support |
|:----- |:----- | :-- |:-- |:-- |
| 0.0 | 0.81 | 0.96 | 0.88 | 50 |
| 1.0 | 0.95 | 0.78 | 0.86 | 50 |
|avg / total|0.88 | 0.87 |0.87 |100 |
#### Fourth Model: VGG16 + Dense Layer + Data Augmentation
##### Classification Report VGG16 with Data Augmentation.
- Model_name = models/BM_VA_VGG_FULL_DA.hdf5
- 100 epochs.ModelCheckpoint. Best Val Accuracy
- AUC: 0.9612
| class | precision | recall | f1-score | support |
|:----- |:----- | :-- |:-- |:-- |
| 0.0 | 0.88 | 0.88 | 0.88 | 50 |
| 1.0 | 0.88 | 0.88 | 0.88 | 50 |
|avg / total|0.88 | 0.88 |0.88 |100 |

#### 6.1 CNN Architecture:

All the layers have a Relu activation function, except the last one that is sigmoid, to obtain the probability of a Malignant mole.
#### 6.2 iOS App
As part of this project I have developed an iOS app using the coreML libraries released by apple. The advantage to use this libraries is that the model and the image are stored locally on the phone, and internet connection is not needed. The keras model trained before is converted into coreML model and loaded into the phone to make the predictions. Below is a picture of the app and two examples of results.

- Example of low risk mole result:

- Example of High risk mole result:

#### 6.3 webApp
In order to kae in consideration the user of different platforms, I also create a web App that can be accessed on:
http://skinmolesrisk.ddns.net:7000
This app is responsive so can be used directly from any mobile phone or web browser.


### 7. Next Steps
- Publish Ios App
- Create Android App
- Improve model with additional data
### 8. Disclaimer
This tool has been designed only for educational purposes to demonstrate the use of Machine Learning tools in the medical field. This tool does not replace advice or evaluation by a medical professional. Nothing on this site should be construed as an attempt to offer a medical opinion or practice medicine.
================================================
FILE: _config.yml
================================================
theme: jekyll-theme-cayman
================================================
FILE: notebooks/CNN Layers Visualization.ipynb
================================================
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# CNN Layers Visualization for skin cancer detection"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"%matplotlib inline\n",
"import numpy as np\n",
"from skimage import io\n",
"import matplotlib.pyplot as plt"
]
},
{
"cell_type": "code",
"execution_count": 54,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"imgb = io.imread('../data_scaled_test/benign/bimg-1049.png')\n",
"imgm = io.imread('../data_scaled_test/malign/mimg-178.png')\n",
"imgb = io.imread('../data_scaled_test/benign/bimg-721.png')\n",
"imgm = io.imread('../data_scaled_test/malign/mimg-57.png')\n",
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Sample Images. Benign mole and Malign mole."
]
},
{
"cell_type": "code",
"execution_count": 55,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAloAAAEgCAYAAABsCt3QAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAABJRU5ErkJggg==\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x1a410f6da0>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"plt.figure(figsize=(10,20))\n",
"plt.subplot(121)\n",
"plt.imshow(imgb)\n",
"plt.axis('off')\n",
"plt.subplot(122)\n",
"plt.imshow(imgm)\n",
"plt.axis('off');"
]
},
{
"cell_type": "code",
"execution_count": 56,
"metadata": {},
"outputs": [],
"source": [
"from keras.models import load_model"
]
},
{
"cell_type": "code",
"execution_count": 57,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"model = load_model('../models-backup/BM_VA_VGG_FULL_DA.hdf5')"
]
},
{
"cell_type": "code",
"execution_count": 94,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"from keras import backend as K\n",
"\n",
"def activ_viewer(model, layer_name, im_put):\n",
" layer_dict = dict([(layer.name, layer) for layer in model.layers])\n",
" layer = layer_dict[layer_name]\n",
" activ1 = K.function([model.layers[0].input, K.learning_phase()], [layer.output,])\n",
" activations = activ1((im_put, False))\n",
" return activations\n",
"\n",
"def normalize(x):\n",
" # utility function to normalize a tensor by its L2 norm\n",
" return x / (K.sqrt(K.mean(K.square(x))) + 1e-5)\n",
"\n",
"def deprocess_image(x):\n",
" # normalize tensor: center on 0., ensure std is 0.1\n",
" x -= x.mean()\n",
" x /= (x.std() + 1e-5)\n",
" x *= 0.1\n",
"\n",
" # clip to [0, 1]\n",
" x += 0.5\n",
" x = np.clip(x, 0, 1)\n",
"\n",
" # convert to RGB array\n",
" x *= 255\n",
" if K.image_data_format() == 'channels_first':\n",
" x = x.transpose((1, 2, 0))\n",
" x = np.clip(x, 0, 255).astype('uint8')\n",
" return x\n",
"\n",
"def plot_filters(filters):\n",
" newimage = np.zeros((16*filters.shape[0],8*filters.shape[1]))\n",
" for i in range(filters.shape[2]):\n",
" y = i%8\n",
" x = i//8\n",
" newimage[x*filters.shape[0]:x*filters.shape[0]+filters.shape[0],\n",
" y*filters.shape[1]:y*filters.shape[1]+filters.shape[1]] = filters[:,:,i]\n",
" plt.figure(figsize = (10,20))\n",
" plt.imshow(newimage)\n",
" plt.axis('off')"
]
},
{
"cell_type": "code",
"execution_count": 59,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"layer_dict = dict([(layer.name, layer) for layer in model.layers])"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Model Summary"
]
},
{
"cell_type": "code",
"execution_count": 60,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"_________________________________________________________________\n",
"Layer (type) Output Shape Param # \n",
"=================================================================\n",
"input_1 (InputLayer) (None, 128, 128, 3) 0 \n",
"_________________________________________________________________\n",
"block1_conv1 (Conv2D) (None, 128, 128, 64) 1792 \n",
"_________________________________________________________________\n",
"block1_conv2 (Conv2D) (None, 128, 128, 64) 36928 \n",
"_________________________________________________________________\n",
"block1_pool (MaxPooling2D) (None, 64, 64, 64) 0 \n",
"_________________________________________________________________\n",
"block2_conv1 (Conv2D) (None, 64, 64, 128) 73856 \n",
"_________________________________________________________________\n",
"block2_conv2 (Conv2D) (None, 64, 64, 128) 147584 \n",
"_________________________________________________________________\n",
"block2_pool (MaxPooling2D) (None, 32, 32, 128) 0 \n",
"_________________________________________________________________\n",
"block3_conv1 (Conv2D) (None, 32, 32, 256) 295168 \n",
"_________________________________________________________________\n",
"block3_conv2 (Conv2D) (None, 32, 32, 256) 590080 \n",
"_________________________________________________________________\n",
"block3_conv3 (Conv2D) (None, 32, 32, 256) 590080 \n",
"_________________________________________________________________\n",
"block3_pool (MaxPooling2D) (None, 16, 16, 256) 0 \n",
"_________________________________________________________________\n",
"block4_conv1 (Conv2D) (None, 16, 16, 512) 1180160 \n",
"_________________________________________________________________\n",
"block4_conv2 (Conv2D) (None, 16, 16, 512) 2359808 \n",
"_________________________________________________________________\n",
"block4_conv3 (Conv2D) (None, 16, 16, 512) 2359808 \n",
"_________________________________________________________________\n",
"block4_pool (MaxPooling2D) (None, 8, 8, 512) 0 \n",
"_________________________________________________________________\n",
"block5_conv1 (Conv2D) (None, 8, 8, 512) 2359808 \n",
"_________________________________________________________________\n",
"block5_conv2 (Conv2D) (None, 8, 8, 512) 2359808 \n",
"_________________________________________________________________\n",
"block5_conv3 (Conv2D) (None, 8, 8, 512) 2359808 \n",
"_________________________________________________________________\n",
"block5_pool (MaxPooling2D) (None, 4, 4, 512) 0 \n",
"_________________________________________________________________\n",
"sequential_3 (Sequential) (None, 1) 2097665 \n",
"=================================================================\n",
"Total params: 16,812,353\n",
"Trainable params: 16,812,353\n",
"Non-trainable params: 0\n",
"_________________________________________________________________\n"
]
}
],
"source": [
"model.summary()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Block2_Conv1 Output"
]
},
{
"cell_type": "code",
"execution_count": 102,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAlEAAARiCAYAAACEQqLnAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAIABJREFUeJzsvVmspdl5nvestf5xz8PZZ65TQ3dXV3V39TyKTZHUDNmC\nYwUOLCRIFAOOFSDITYD4Ole5MQwESIAARhDZsS8iA5ER2RIZiaRIURy62ewm2V1VXXPVmc8+Z8/D\nP66Vi7XPrupJajEXNoP93lSdfc7+x7XW/37v937fL4wxLLDAAgsssMACCyzwN4P8930ACyywwAIL\nLLDAAj+PWJCoBRZYYIEFFlhggZ8BCxK1wAILLLDAAgss8DNgQaIWWGCBBRZYYIEFfgYsSNQCCyyw\nwAILLLDAz4AFiVpggQUWWGCBBRb4GbAgUQsssMACCyywwAI/AxYkaoEFFlhggQUWWOBnwIJELbDA\nAgsssMACC/wMWJCoBRZYYIEFFlhggZ8Bzr/vA/jr8Kvy7y3eS/MIbv3LF3hua4f399ZIewFyItEF\njSyleH5GIYgBkAKODyoEDzwAos0UlEFMFcYxyFJKECYksUsQJnhOxiTyifo+cmCHhS7lyEKG0QLl\naITUaC3JJw5kElHIaDZGAMSZYtQPYeDijCVZUdvjaMaUixGZlozaRUQioZxSqk5RwtDvFQDwwhTP\ny3BVTueoggozwjABwJGaJFNMRz4mVriVmPXGgPt3lrn4e2/R+QdvUNpN0Z5EJprgcEJW9XH6MXIw\nAWD09DJRTeGNNcX/+x1ks8H0hbO4/QTn1h7C90geWyYLFOH2AOMqRJozPVMh3B7Y63H7PvLCFsZ3\nyUr2uqIE7v4AkaSka3V0oOzH4xSZ5JBp8mqASHMAhAH54JDkqU1konF+egc9maDWVknOLpHUPIq3\nu7B7SD4YoC4+xuDKkt1mYqeCO8rQSiBzg/eTe4hqhd2/tc6/+O/+Kb/93d9D3gtBgjMSOBOQGUxX\nDGlFIzJhz6WYgzKQSkQsccYCJHg9gYogqUEWGnu8sf2OTEAloKLZqceGqCkQBrIQ/C6oyJCWBdGS\nIVtKKTUmjAcB3r2A8AicqSGpCNKS3YZ2QbuGrGyPzetLVARp2SBTARqMgrSi0cUc4ecUKxHrlQFH\nI7uRaeySPShSuS0oHmrSguDwTc1zl+8z/dIhX9t7j4u//19Tv2b3d/zFhPCWT+N6ztErNo4M2oLg\n2ND61i7d19YR/+URezsNHvtXmqMXAoSGwaWMc3+ombYc4qokaoIzhbXvjO3c/E8D/COF9g2l+xDX\nBcU9g5HQ/mKKd+giY8Hyuxl7X1S0fmToXJY0rmriqr3G5Z2Mg9+NyB4UOf9HMUnFZe93EpzrBeJW\nTuWGwpka/L4m9wXTJcnGHx/SfbnF4Wv2mlZvSCarhtW3coabiiwUrP3T7+KsrZLtH6Ceusjt32mS\nrKe4xQTn/RIqhqRmWH7HztvRmqJ3JePLz1/j2999mpW3YHhG4rzZobdfwe0pqjeg84zBHUrSikYm\nAqMM7ll7PdzvlYmbBu1AvhZjRg74GuFoKj8MmK4ajIBsIya8HqBe6zI8KuFWYtRVe2+Ti1MaXw9I\nS4LBxRw1kZz744jxmk9SEgzPgtACmUD1rkamhv5jitKORqb2esRVQeFYc/C6RGTgDQTjJxIu/5M+\n+fVbdH73dZo/GSByQ1byEAaMIzBSYIS9L1HTITjJyIoK7Qq8XoaRzNec4RmPoK/JAkFpN2a85lPc\niWZzY7YmpJrJskfp/oSs5OEOE7KSi1YC/2BMvFpEpZqk7OINU+Q0QyY5/UsV3LG9L5MlRf36BONJ\n1CRDpDlGCZJ6gDtI0KGDmmTEDR+jBJOWw3RZMD6bU/nQHkfxIMcbasxMQslCyf7fTVj7Q4+9L8Nv\nvv4eX7t5mWzq4IQZjpuT7BSpXOixUh4C0B4XGX7QxAh45c3rfKF+i//1f/8tVAzj1yc8vbHPB7tr\nsB3SvNJmvdSn4KS889WniJftWvibr73HreESd46aZImD42WkvYAvPHuD/UmFKHMYTAMCN6M/CvD9\njGZxwmG/TLJTtGNsY8zLm9u8/fXLFPcg+/UerdKYzrjAeOrhvVtCuxBfmvJ7z3+b3bjON7afYLRT\n4eXnbwFwsXTEH/zxmxT2BaM3Jjy7ucv54gnvv6T5U/2vBX8NxH/o785bkKiPQj5zCbGzT97rox4/\nT9aq4PSnYAwiTiGxK4cJPEwxwDh2pujAxQhwT8aQa0SSYqYRutcHQLWWwHNBa0ynZ3fmOohCYb5v\nUwoxvmv/7yrkKEKMppgohmoJXS0QrRQwShAcTgFw9jqQ5+B7GM9FZDlmPMGMxojAB6nIj4/BGBAC\nZ3ODfLmKiPOH+w1d5Di25+Y66FLAdCVERTnun71D/pUX8a7ugDZQr9h9DMfobheTZfPtqGaD/KQz\n/9m5cA4zHJO328ggQHiWGOWDwcPv1Krks2v0KFStikkzhOs8/L0Q9jz+P0C1WuTt9kc+c85soqsl\n9PvXH344W9xP9ydeuULwT464/uePUb5vcCeG0v0pTnuAiFN0s8LgiTKjDbuQ5oElKiKzpClsG4qH\nOd4gRSvJeN1luiTxBgaZgjvRpAWJzA1idmuENsRVOf857OZkgSQNBXFD2IeYsWTLHxgwlsSkhY+u\nS9oVGAXOxJIDlRrisiL37e9PH4a5D8MLgLZkFD37vgfhoaBxPUVoSIuS42cVXB5y9j/5Ka//OOXb\n//gXCA7GDJ4oU74zQu60oVxEaHv9xpdaFG4ck9+6S/S3X2Vw1qF2O8X76ttEv/UqhQdDxDgiv3UX\nZ22VybObiNwQ3jkhu3MPgPRXXkJ7EqMEpR8+IL60jvrmjzBfeJ7RZkDt3TbGc9EffEjnd1+n9YMT\njOcgdtvze65qVe79N0+z9H5G+G/eQq0sE105gzPOSCsuzjhDfuc9VLNBdmkLpzMmXS4hv/Uu6qmL\nABz8YpOkJjjz1R7T9SLh3hj93tX59Z789ms4E81ozWH5q3fRKw3aL1cJO5aEAOSeYNqU9C4Znvxn\nJ+TXbhL/5ivsfslh8xspRlmScfKMQ/P9DG+Y4vRjDr5QIw/sfhrXUtxxxnTJY9KSlHdyOpcdardz\nSneGtF+uUt7JmC4pGj/qMLpYI9ybEi2HDM468zG29ie7tL+0Qe8yLL+tKd8aMDlTRnuCaUMyPA+N\nDwz1tw7BdUhWy+S+Ivzuh3YbxQLtXzvP8cuaza8bCrtT7v3tMo/9s/tkO7skv/EK4f0eHPcQjsJk\nOcQxOo6R4exkfB+qZcQ0Jjm7hHf/GDOZIMolkBJdsH9nfIXcaZOfXUGNYjjpQbNmt3HSQ2+2kA+O\nZgM3R1Qr6EoBsdu2kW+WwXITdg8RjRpmGmFaDeTERi7GUdAfQhzb9e50OWjUMIUAMZyg28fI1WUA\nRldWKWyPOHq1SvWODUrDD3ZB2XXABHbNu/1frLL1tSlJzaNz2eHM799k+MULuIOM8MNDur+wicwM\nccU+T8brgtUfxAy3PHqXbBDSuJYxaSlkBio11L+zTXq2RdTyiMuKQjsjvHWM2dkH4Og/f4HcF5T2\nctxRTuHmMeNLLU6edmlcy1BRjteN0IFLXPdwxxnjNY/ifkJct8+h8YqktJ9T/skRxncZPNUgrkq0\nA8WjnPDfvIUMArKXL9F7ImS6IjACtv6kx96X7X0Zntc0fyzwhno25uDwNcmF//57n4tE/QevRC3w\nUWTNkGzjCfxODP0J7n7Xkp4wQK82ma9ggPEcjLAPHKc7IauGpMs2wnNOpshcI89uossBZngqL7iI\nasV+P0kw5QJGSuRkRph8d67SkM4IShyT3z4GIPA8hBBzQkKlDL4HuYajY/LRGOE4dpJLOyGdwD4t\nTRRjohh11McMh+jp7JieeZzpVhWMwR1luA+OKe20wffIgOGmT1GdIdgdYB7sQan4CSICYMaTj17L\n2cNPOA6yXsNoTX549JG/EWGIU7LXLNvZtZ/5Piw1kFlOdn/7kR18fgIlHOcjBO8U+hECNz/O7R1k\nO/jE57JQQE8mYAzqZEjJjUkrVqGo3Y5R0xQT+GQrVYwAJzIU9/X8+0lZMG1BVjIMqpAVHCoPQCtB\nVJekRZCpwM3teWkX4prEqNk55JBUIQ8NaiowSuH3NQiByMEdGQpHOSrKSSsOWoE7sWrUqaqGsaRH\naIMTGYLDKUndx1QVUVMgMygcaip3Z2OBEHdi8Hsamdpz6T7pMV0x7L/h4I4E5W2NO4Ioswf6ldI1\nfnDyIvq9q2RX3kDkhuSpTbQSBD9+YM9Ft2wQgT3H+ocxwYMe5plL84Agv3UXZ3OD4csblN/ZI3pi\nBbSekxf5vev0/s4VKrfGjF84Q+E7H2KKRUR3QsGT5Dduoy4+hlpu4U4NeclH3T8kPz7G2dwAYPDq\nJsGxoXT1hBwQUhLsDhg/VscdZ7hHQ/u55+Hu22BHZKfX0v7be0bjHyu0pyh898YngoDytQ5ZrYBa\nUiSPrXL8XIHCUY7Xy4jr9pFQujfCHRcQ2kEMJ8jnLpMWJZvfSHHGGfGSx/EzDt4ACttDJmfKuO0x\nKjaExzNiuuLQ+n6PyXKD+o2E7kWP8ramdKOP7I+I6zW065D7gmSlRFRVjJdLZAWBiu02qnczkrNN\nkqrA64J2BMZzKF5vkzdKRDU7N2VqSDdqqEmGjHL2vhCwHj8OgPrmj6j/8wOa710mWi1ycqXE8uv7\nmP85QdWq9M87FG6kmDRBD2NEsWAJTZ7bABEQroeYROAo3IO+JTtS2XUNEDv7iFoVk7gIKVHDCOO7\nSCnJSnZ9cyYBIjfQqsPOAbgOTCNMs4x0FCZJ7DbTDHwf4yiEtKT8lOyI4QTCAKMNIvDRnS5iax3i\nFOM5MDve0+MqbI8Q2wcseQo1X+MVJvAQcYqIEnAURkFS8+bz2wyHFO+PbFAc+lRuDZmuF0nLllMY\nBflMdXf7ds7FNTkLYiB8kDN5Zp3dLztUP4TRWYF2HPrnV1n72sN1Mq7b7Zz5tx27Hl9qkfsQHE2Z\nrocMtyoUjnL8kxj33iFCrwEPAzFnAkE7saLBnQcUagWCjmK85uEOcpwL50hXqnZM72eU9gwyNRhX\nzdVwkUPUFJT27DWbLim2Xtzl82JBon7OMFn2kDk4Y4WpFdCeQjXLyJvb8OFdq+4AuB4y8O1kB0yW\nI67eQADO2ip6pUG62cR4Eq0krpSINCcPXcyMaMlphg6d+SItHuxBp4uq1zBpCtMIGjXM+Q3UNIGD\nNvlwCEo9PA7AFAKrXGFNeCbNML2+je60gTR5GFW5DmQZolFHnapqN7cJb4t59JT3B8hmA1O1km7U\nFFRvZdDpo8djnEb9UxUkHUV8KpTCTKefqjjpbg+5vmrP/xHikzdKZCUP596DT92kcByE43zqPj+u\niD0KE8ef+vkntmMMejx++ON4wkbYo/XkMYe1KkaGVO86GCWIalbVOVV5ALQCv28QuSSuC7IQsgKM\nVhVB1xCeaMq7htwVRA2BUZK0JBhv2BQfgBGgIkFaMiStjOmmINhzKO0YghODnJEvlWrMRJMWJTIx\nqCif/26y4tE/L9EuuGMIayWcSGMUdhsp+D2NGicYJWhcBZSA3BAt2zGW+5CWDELbVE3uCkaXEn7t\n8Q+5d3rN9ztkQHiSkZU8/JuHmEJA+tTm/Hoa146v8Zqk/t6Y/MZtxv/xa8RVyfKf3EUDvTc28QY5\nZjjE7VfJW1XaL9j5snT1Bt5AY5RkuOngzwhxcqaCE+UIx2H/V1dY+X5AaTtC3T0gb7cRjsPxV7YA\nO5ZrtzPyG7ftdy/ah4Z/EpPUPTxH4aytYqZTzErDpoV+cgdxZpPphg1+HvvXCe1nQ/Kii1Jqrm7K\n559Cv3eV/NpNTv6rN5i2BMU9RXk3I6oqkpJH8dCObxHnuMMUb2jnxuDiJpNlRXCSgRLIxFDcMyx/\nYxdTCHAmOaI7oHa7NE+BuQWFebBHsVZATRKmyz4qhrxqAwK/a1j+9hHDZ5ZIqg5RU6A9cMaw9J4N\neJz2gPGllh2zMxWz92SRyl1F1PLIQoHfgWlTYqSP0B7jVUVx16D+/N35/BCOw3SjRFJWVO/GHP+7\nNcL2d1GVCkHHYDpdTJohW0uWmBQKmKyPPFXidY4ZjWCpAcMxJo4R5fJs7k2tKh0nMBxhHAfRG2JW\nGuB7VpEC8lYVOY7RRR/pOpakFUPUyRDCALQGbaw6WgzRpRCkJC/5OIeztSnLMH5o/+86iNmayDRC\nao3ROSLwbcbguIOIYpAKZ79rSRqA61ryJMQ8Y5E2cmRmSEpWmRZbGxy+WsFIgUxquH/2DqG8Qlq0\na27lgaZ4p8dkuYk3hNJ2NFecmtci3PaY9utNjISsIHCH4E4McV0yeH4FgPBEM7wgic4n5N+yY6J4\nvY28so6M7ZgUORgHupcLVMIN4rrD4JxiumLXj9Y7BvXeTdhaJ3/hSUZbIX4vI+jkpBWFfmIJrxuT\nhx4YQ3i3S/+5JY6f9Vl5214Prxsjco3qjsmWymB87my3uMinr+0fx4JE/ZyhsB9bZaltc9NKSZva\nCQP0YDCvFND9wTwyVZWKTVHN0mUmSRDbB7hhaAmO5yInEUYKlDFknh3QwoDTi8hLPslyETc8i2r3\nMaFPXg4QuUYOI+TJwG5nax2pBHnJZ7T6kESV7o2suuS7mOoasj8iP2pbIjWDDAJEuYzwPRsZ+S7M\nUofECbrbtcc0IydCSk7jGa9vcNqDuYqU7ezayP5RUvTxVNvsZ2dzA1Mpkl+7+anXW3jePEV6ChPH\nOMdDZByiP/VbYLLsU5UmZ3MDUwjgM0jUJw/gc6YIs4xOUmS1OOQwbqBigzPNyUJF4cimX0RuSCp2\n0Z02JSqBQjtn6e0BedlnuhaglZWzycAZ5+R1B4xNqQUdTVKWpNVZyqegyZZyCrUpUhrGgwCRO7gT\nG+1pRzBtKpgJ4klJouugnUc+qwiS+kOlK6kIRK4I24bK/Yxwb4xIMoyUROtlO0ajHCfL8bv2vjSu\nGfyuIi0JigfW61FqTPhb9R/zv3CRL4ea/3F3D/2lFyi+u02+3rSRvaMYbdhxWr4fwYd3UbUqQoPs\njxCVCidXFOf+sDv3Ek2bktr3djBKMTlTZNpQ1G4l89tQunrE3d9Zp/Xjh/de5AZyg3jmIio2yAdH\nZM+cwaw0od1GtZaYrNoLUtrVBH/01vy73ScCmj8ZoW7v4pZLjJ9aoXDSQ5TL9J6sUP2gRz4YICYT\n3LU6APKDO6gnn8UZpYhyCTNTdKOVAt5sTOWB4MyfDnGO+qi1OoMzRbQLQd+uIJPzFYYbikJbIwoF\nJssKoQ3edz9g8FvP0X9MUbtplVjx8jNkRcX06Q3C6wdz1US1KujxGPG9HxP/yktkRYNKDWqcMN0q\nU95O0fd3yF9oUTxIaH6g0a6kcG/wMHVdqTD+8ioyNdRuGupvH3D8hTV6j4doFyr3MwZnHfyBoXJn\nzMmVEsWDnOJORPJrLwHQfsGj9V5K73EXmRqihk//uYQVACko7kZW9c5zTOhDniPKRVQcW0WKhyq2\nkNIGj2FAutnE3T62toE8t8QripGtEvrgCDkjOCKy48OUfMQkstto1hHTmLxaQD44skFnllkVKvAx\n5QJ50UMZY1X/mWpvshwRJZg4xrTqIIVVpwDjueA4NsWoDfk0QmqDKBYwpRBh7atzS4aYETbRGSKn\nVYzMCU80haMEXS1QvZvhjFLGGwHqSy+gleR00S3esgFCoZ2TTiRpySEpSco7Me7+AF0tkJYE4QE0\nrsUcvuJz8oxg/TsJ4e0TuxHX4eCNJt6eR9KQ+K9cQScZacVw7+/asXz2j/qooz7iuXU7phJDUuHh\ncRzEiFKRaKNCHigmKxKVKirvHaILgX2ujSeM3zxP9Qc7mMGQSsFH6DKjjZny/LRH/WZGqTvGKMnx\nsx7/wxt/wL9ik8+DBYn6OYPIDU5vgr5zf/6QVq0W6ZMb6KfPIGcyrppkNtVwMoQ4QW7ZQWiSFPxT\nb9IUc3xilZi1ZUwxQOwdI388S4X5PnJtBZFkuKMp+f4BWZbZB01hEx3YQaiSFPpDBCBcF9lXVDr2\n4SSmsd3PzGOgWkuYcgGlVubeKz2ZoKMIMVfN7L+nKY7s/CrJi2dxB6lNXxYC+pfrpAVJ/bqPdoHu\nI4TJGLKdXVSzMV/8jDEfUXmk7yM21zDDMewdfuq1lkEAm6uYnYOPHBeAPmzDp38NGQSfqXrlB4ef\nSq4+DarZgDT7iEfrI79fWZ4TR90fkJmQH3+4Rf09RevtHrI/xhtPEY4C37NpkcqpJ0qgEoN2BXk1\nQPUj/MDK4FkgyEKBTCWFY039RoqKLSHTykPdnZEoVzI6o5isS9yeYuV9Q/nuGDVNGTxRJi0KqxJF\nEieepT1ywIG0NJPjp1D7gaZyrUte8uk9WSL3rcE6vGU9SsJxkBfOoj1BFkiMAzI3+Nf3APDDAP+k\nymQ9wB1rZKI5+bDK/1T+FRwe8I8Pn8dZXWFUcXGW7eLcfXWF0oOI6oc2GJEPjtBZhgxrbP7JMd0v\nbFJ/64DV7yWIaYJaWcbc36V4VEcfn9D/j54nqgtWv36EvnPfjg/g+AtrxE1N8dvXOXX15YGi97jH\n8tspheMcpMDb7dv5WatiysW576v+tRvkQPZLL+F880dkobBFDCcdnDDESEF+eETy6y8zWZaU/09L\nNkyW0XnaKmJ19TjuxKB22pb8XXwMDo8o/GSHDMi//AJxAwaPF+HxIqUHEWt/YediXrQEaHg2ICsK\nCj+NSTebNK9GZKEi+YWnOX5eUrltU7LO+bO0nyrR/HEfedxn8vQaB2/YbbhD2PzABnCdyz7OGJyp\nhkzj//HbiFeuEP3ys7RfFCQ3A0QOQV+Tl/1Tjk306hPEdUHhwD7wTadLcb/JcMtDxZYIJBUoHBkm\nGyGdZwzluwojQ2o/tYHK+iDE3e+SB6vWmH0zQrtWzcl7fYSZqcx5bklOa8mqQsvNuX9H1muY6RQc\nZUnJeIIaxjZ17TjIeh3SxCpDUto1dTQC10O3rdXB0RozjZBZboPO0McoCXFs16YwsOnDKAbfRfUj\ncGxqUGR2NOnJxNonhkOUWQHXs2pS4IMjEd0BulZC7B8jazaNRRhgfBcxteufKYWIOMV0bFpSVCsY\nCUYJnKkhCy0tcPsJ7vYxqGVOLge0fjTCLdr1I20VGK95lO9OmbQKpKFLoZ0jtOH4jWWW/vKA8k4B\nr5eRVhRGQvUWeF/74XxexL/5CjowVG4LnKk1yesfX6P02htEzVkRyAsViodFMDDa8AhPMow0LP/Q\nrifu1R301jJGCdxxRuFIIlPD5Iklpi2H0m5CWlxm0pIUT+0Y124TVp+if8GOgaRivZ0lQGaa4Njw\nzd5lYPip6+7HsSBRP2fIQwcdlPHEBcDmyM1wiLfXQ5dDyB+qFsZXVkLuTxBaW/N5kqJLBdAakeUI\np4YphphiYBeEchGVziKnKEa3Z1GDUqjNdcg1utNF3t5BKmWN51mGGVmJ+zTlJpxZhV8cI3wfsbGK\nCD3oDOG4h5HCmiEdhfRWyaohcpIgDk5AG+uJ6tqF3QFUx7OpvlxDu0sFiFfLmDgm6Gq7qNWq1pfQ\n69vUXJ5/JpkRnoeIEvKTDibLPupRmqUjTJYhuwPyyeQT3z9NpTnntsg+ltL7q0jS5yVQAPljGzj7\nXfgMEvWof8tkGTd6LcgEhbZGdoaQZXPTvGwtITIzr/IpHgiMtAbi42dDZBoiNEyXBbkHKobwyD6k\ntCeZtlziqsAfGKrvz7w4hycsLdWYnq2RFTReLyMrOow3A6tYFe2iXNqJcHc7hMtVhheKaFfgjuw4\nbV6NcH54g3xsvXKN5CJ5OFMgXQd18TF0tcB4JbTG9tQgMsg9Sb7Zmt0MTbTiz9S3DLc9xhkucdAv\nswl80F/D1ErIRJOVfesrcis4wxg5tH6n9PF11E8m5J0usj6rhppGOFEOjppf68mSJHzpEu5YU74z\nhZMustmw96A/QCWGzW9qRLWCPL+BmCYUv/Mh3X/wNEZJoqqi7LpkN25bL9XyEvSHVB7YCsz8pMPk\nt18j9wT1jXXW/qKHGE3JgcnTaxRvnECrxXjVpXr3kaKJWpXytp23vYsFGu8P0IPZQ0DNVAw9q/Ba\n9ijdN7gTzWDLIXdDlv6yT94oMTpjVWhvqPEGmumKT/n9Y8QkovcbW7gTQ+tHDyv4vEGd8naCuLfL\n5PWL7H7Zscob1q+CFMjnLpMH4Pesp2lyrkLwvk0HF6+3aTZWieq2iEErSOoe4TOXANj5FY/WO7Zg\nISlLsqfPk4cKlRjK2zHjVZ/6jZzKn14jevUJjCuYLhtqt/O5AqTu76If32LasA/zLHTIHtbLkJYc\nnLVlxHEHM51aUtHpImpV9EwFNlrb9N0kQg+GiEIBsX+EqVcRgY8oF9F7Q+RSc+4V1dMI1agjZ8Gb\nGU+tIVxKuw7XSohc21TeNLKqdwmrSHku4vAElmrQ6c+VqPm8aNQRI0vq0Ia0FuD0IsxKk6zq4+4a\na1wvFKzpPdPWlA42c+C7lkCFISS2IEOmhvB+j85LTZKyQ/FQI7MGIjM0PoyRk5TR2sxTO1VUHkQc\nP1dAJbD81bsMX9siCxQyN0wfX+LgdYma+qx9L2XrjzoMLlfRbz6Pe9MGP+G3rvLk3llEknH4ZhN3\n4lN9D0p7Od5IEtUlpb2Mwnc+tMT1tS0KtzqsyqatYAai52waXKaG6ZKL383wujHRcog30hghGJ6x\nacF5dWqjjuhFND+wz6i4pmh88x56uW4Dm9TQjQssSNT/T+H2I+QwstV1notuVhClEHN0gjjuIJbs\ngp43y6A1ecEhqdZwBwnOUd+SooMjRL1Gvt4kqQd43ch6qlwHs9zEnLWqlbi7+1AFEQIlBaJWRbaa\nmF7fpgxHYyuDZxmq1YJW3RowZ5ETnmvJ3TRBjCObxz9dmGZGXhElOFgjPFhT40c8VXECo9FHPEuq\nVbfbEQJ3rNFRhKpW7EKxvIRyvU+Yy+dE6TT9eXyCrFbmROoUzuYGZjgk7/XJ9g+sIjX7/qOkTPg+\nxAkfx98a7KIgAAAgAElEQVSEKP1VED+6hqnXP9/fOg6Bk+E2IgbnSgSdZVs6vdKwJdAlDznN8I/t\nfZGJh3EkcVXZUm5prOekaNAeiFyQVAVx3UFm1i+FscpRtGEX0sCR1mdwv4fxXQ7fqDJeB3csKD+w\nJeaFdoZ7v022u4fyXPyuj5EOyUyJSiou7tkNKPmISQqZRiYZ2nOI1ypkBcVw05rMVQLhkUGlOZmn\niJrWn5G7wnqJ7syuuzH4PeiP7RgaxAHqbI3+OYfWj+wDbemrtxFSkl6wfreo5RHOiNzxK03q//x7\npG88B9jWFqpWZfILF4kbAvfBMeIvd4h+61VCszFvX6EPj3BiTWF7xPjKGklFUbk5hPsR9RsZ0/UQ\nlZp5gcLeLy/R+skUeeM2ftemDswXnqd7UXH2X94HIZC9Ebp9gnNuCzOyXqnsl16ifm1kVYwZ0ucu\nEDyw5Ha0sQzv37LK78XHMKdewhkRdGJNcTfB2+sRVdcQGtq/uEpSEVQe2HMpbI/oPVUh6OToO/c5\n+oevzNM7Sd0qTSt/cJW818d57jIHf/8p3DGU7kPQsfO7/ZIg+PXLDLckwYmh/CDh6CUfIyWbR1dI\nGgFZyaP7pEDmUL2bk1Qk3YsuSdlWTlVvQO3tfdt2wsDoTEBUF/h9Y8etgspPOugnzzI45+EOAGmL\nFUZP2wq1Qjmkf7nKdFlQvZ0zaTnzilKAuOYQ9kc2AMxzTKeLHo2R2tiqZcAMhuB5kOW2JUmhYP+m\nXgXXpvznxTJJav+mXLapzdMKv2lEPhziNGrWylArIftWWRLFgg0SJxOE59kKQZ3bYh5tMFMbyMlW\n05KxWZoRx0FXCqiplTKzZojTixCOQg8mtvqv4FpPVPjImloMkFmOLhUQSYpMbVClSwEyhbgmqH+Y\n2SxEu48ZjqBZR83EfG+skdOM3mXD6neh+6VzGAnhv3mLIAjY/4cvklUy/I5D4YN9+5zSsPfFAhu5\n9fkZJTCuxDsYkpYEK39+RA4MzyiSiiBsG4J2hNlap/1qHXds0NUCuS/Y+5XW/FzqNxL89pjpcpWs\nqHDGiqQi8Xs5vcc9qnczVJwzfG2L8g8VZjAkWjtD1LDzQithMxaigTrsES6FHIzLVD8r1fAxLJpt\nLrDAAgsssMACC/wMWChRP2eYnCniDgK8ozFCayvNJolNXU0myL69pTLwMJ6D04uQvkNW8shKLYJc\nk23voA8OUdMpgTYQBlbC9l2M5xCt2gjfbDxJWpQU92JklGJyg5hJwdnlc8gkQz44wgyHyGbDRlAn\nPXBdsvVZikNJGyUpifFcsmqATHIbgWlte09lGrF/ZFOAzRrytD3CDMZ3MYGPU6tahSvPiVbLNurw\nPNKixGdm+sxyTK8D2nzEEyU8z7ZsOK2uO43K11c/YfLOtnc+uv9HjN3CcZDNBvnhEfrFS4hJAvsH\nD//4USP4p5jChe/b+/U5zOJmlo4Tvv+ZVXuPbrcZjDnyS8gEZJSTVz3G50o2daoNKnTICjZuygKB\nE1mfiYptewGtBMVdyIq2Wm/4eI4Jctwjl/DoYQpueMYqiN0na5R2cyo/PUYedlh6z8WZFCi0U7xu\ngvEkRgpGL2wgn1knrin8Xk7QyRHaRoGTlmLSslU83tAgM4M7ynFHp80MbZsDdzzrNzXUtmJHMm8W\naCQUjjT+cYKapky3qvQv5VzcPMQA3UnIxkmEeayM6oxs1VKjTnKmTjYr0y7sTq1X9bknKbTtGBme\nD6m/dUgex3BhizyQeD3D9MkV3LW67W8lIFmy3goXq4rJww5yKSQNHcw7H+Cc2ST3bVPS+p/ettH2\n33+dynaGGiUYIPcfNmltvZeC51qvi6vQ97fJNp/AefcmotkgDiT+D+/Dxgrpm88jv/MeTj8ma1qF\nMDzJ5+Pl8MvLLL/10apTkVtvZXy2wXhdkBVsY9PwyBCcWGVVngyACuG798mzDG9oCG8dc/c/W0O7\nhuZPDSIMUWvL7L9ZR7vQ+DBCRjnuzswCwCbVf/tTCq8+idueIPsjeGmLwqHB2e/iHEnaX9rAmQg2\nvz5EjWKil5q4I0P9u3YOmnKBZLNBFgjCE1vqnrsFSg8ixhsBTmRIl0t0ngxQMRR3ZsUJs/QUYFO4\nY43XE9S+v0vv9Q1UpB5eD21TX/YGKJAK4cxM5TO13G4ow2Q5qlpB+LaVC/0RohhadSgowXCMOFWe\nwsCawE/306ihwsC2LghDu5ZGs35P/sMCFlMuQndg16z+ANGo2bQdttJZAMSJLRAq2ryk3GljVps4\n/RiRZOB7yIZNT9nzkvP/62oJ40jSjYYtUNJWNRYaxDQl9+xYTWoOwb0pulYienKZ8PYJjavWna52\n2oxe3sLrSaofdDh8s05SFVRfuYLcaRN0NfGeg3ag88VNnMjgTDUqUUQrM4V4y6G0mzNZbtqecI5C\nOA5JVTDZyCnu2WNOWwXqH05xrj9AX9hgsiwpHNlzyT1BXHPQbpnJssTrG8YrIeGxRkWarGD9Vk4v\nQuiA0fMbtj1G8LD9U/EgBSnsWnmhPC9Y+bxYkKifM4R7U5tHV4KsWsABxBCysyukFY9gb5bH3TmA\nJEEEPkopnEKB+PFlRs+tE6zV5/Ku8VxEntu2A4EPuSE4sH4fMZ31EPEca0RUClMu2HJwJchLHvri\nhm3i2Zlg2l3MZEI+HsOpiQ8wvo8oFZFhaPelFLpawAjQniIPFL6zijzuY7KcbK2OTHK7GACiO4Cj\nE/LJxPpPtMHrTDEyxCTJ3OeD42A8d94EU1/YQM+ajbrbx+Q7n+z9cdor6uN4lOx8nMDMCdiNbdvX\n5VHMyJEsFh96soRA+nbh+Mw2C38FPr7/j/eYksUiwrVTOU0V/tQgkwzwkIklSklZkpQkyazPizuC\n4v0h2nMwMiSuClQM1XsZMtH0HvdIy9KanMuaKTOP0yOH70wMWSiItmpEzRZJWczMvpAVbXuFtKSY\ntCTRkpinAsKjlGjWj8hIgTOxXa1Hm7Y3ld9VVO/ZSqC4bBvnFY60JXtj26HZeNZvBbYje3hkze8A\n/fMupTM9fnn5On9GmS9t3uZq9Rnbe+johHwwoPt3nqJ4kOJ97Yf2OGbndPCFKrVbdhGNqwJTClGV\nCuwfUfIchC4TLbkYR1K6M0T2Rjin1rRzW9Te3qfzlXMEJxmV+wnq8hPkBY/CXoSa2PnIq1fwuxnh\ngz7TszWCZy7hffVtey7PP8XJUy4qbuDfPITRCPXEBfrnAmpvZ7B2huLVw1mp/QSzWkatLMO9XXj6\nPADF2925eXf4S2PqNwMeHaVxVeKOFG43wpkGGCnY+M6UpOLSP2cJgLO6aXvxTCPyr7yIig35rbvU\nr6+QFoStvmzWEFpTu53a9NmGh9/TpFWbrgnbKebSOUSqMb6y5CWG+odTsu0d1OUnSEuC6l3N8HyR\nk2dLOCPB8rvpfB5F62VkbijtJsjcoCYJlbsCb69HvLRM8daA8eMVnCkE3Zw0ksgU0oLE79o50n8s\nJCvYTvvZ9g76i5sMHte2Om8+iRRUS9AfzdNrIgznxOO0d54A20sqDK3/yVGW2EgbJIrQVjurasV6\nO48783Se6fVhbXnuCSVJbF+43BIz8hxWlmyDTp2D8hCVMsZRxBdskU1w89AawwHGU1uBdty3LRem\nCWI4xtTK6GrRelz3j1Gd2THOGnbq0EX2J8StAs71rvXvxTbgE9pWt6ZF203eBB79JyvIzBD2R5jb\n9wDIjMEbrOF3HUQUE55okqriwa+XaVwrIFPbSyraSnCmHhtf7yFPBqTFDaKqHY31GynaFQzOKUo7\nhsm5Kn7pMrWbOX5HMlkV9C5VcIc2DZtdeJLch9U/PSC/dReA5Dde4fiKy5k/PKR4HaJzDfbf9JGp\nJK56qMhw+FKIikNWv9MlCxTjSy0GWw5y1quu9mEMvo/Xz0hLDurP36Xzj65Q5fNhQaJ+zjA+U0DF\nBneckXsS7ZUwq2Vr1h2k84mSTyaYPMdpLYEx5EdtvOEQb22ZrFZANyu2iq3sk1ZcvH6Ku9tBHxx9\n4kGvZioTmS39NcMx6s4DVKNOem6FZMknqXuYizUKu1PUvQPMzIwtSkW7sEwj9PEJYjBEuM68/4rx\nXVS1YF/TQhWxfYA66UK9St6wkbUImxjVwihJ7knbdiF0yQNFUK3QP++yckp6ksSa3asl22Cyb43D\np5EcgGrUP7NP0ynkY2fhpPeJ5puP4q/ahlCKfDzGWVslX28iThvdzfr/fFYn9I8cw2dU+Qnf/wiJ\nErPKy/PFm7ybnSFaEozOlUhKEieyC0VcFeT+Q+JRvTVB7Z2glMJd2iCq24Z72hU4o5zSnlWLxuuK\nuKnJZ6+AMa6guGO3UdrLyELJ0cs+43MZSIN36DBtufg929k8K2D7TEkIjg3F/RhyM48kR+u2w3Hc\nEMQNS6aMEqhYoWJboaNia3QO98bIaUq0XiavKbJZNJl7AC7TlkvuCbQnGB6U+XrlErBLzZ0Q7A7w\nuh6stshefgKVmjmBehTjDUPzfXtsjesx0/UiTv1xvKs7yM6QoORz9FKB8ChFv3cVjSU+AJMzJYrf\nuk7mb9i+UIkmXqvgffcDpDHkL15i59e2WH1rSvij++huF/+OQj9CkvPQJW4akqqD2tlFFouMnlnC\nG2l49iKZr/B6Q/K1KmiNd3WH9NIG3u0jnOu2wMGMJzibG2Q7u6Qjb0aoH5LvxvcPba+jVoPgxFDa\n1Ti9iMOXQoaXLIH0Dh3C9uz6+oqoLqmd2aT245P5GwNEkpLfuI13FcxvvsLgrEtSFgTd00Ziis5l\nn7VvtOk91yR3BeXtnNGZgOKbz+PsdFj9336EqFaIrpxh6//RqFHCybMV7v09S8Qe/xc57ru3yS+d\n5d5vlWh+4FH/1j3y9SZqaiv5nFFO8d6ItB4wOBtQeZBR2B5hrtm5Fv7qc0xRBH1LLb2BRuiHThaj\nBEiBrhaQp1W+uf3bUx+RUcru62RkiUYxtP7OWcNKM/Mo6VrJGr6VAikwSYJsWH+XAfu2iGKImUaW\nqI3G4DiWNPq2lxHlovWSugqErc70D2xwPA9iHWU9U1pbv5bvQ3eASRNEGFhvU39iTeqze32qvYhp\nihiOcYdle55agwSVaMaP1XAnmsY1a8juXFpCaFj9QYzudlGXn7CX5+oNnJMpeWB7WdW+t4M3WOPk\naY9pU+L3Dc4U0iBnvKkRk5hsewfn+XXGa/ZImu8MMb7C77gMz9pGpOruAdU9D//iKkcv+aChtKNJ\nSraRZ/EwJ791l+Q3XgFg9xcd0pXEBvlRzGR1hcYHOSq1yrrXz+hc9kkqkDasYhwcTSns5PNK1KOX\nS2S/WCap2Fdbnbv9BFJ+/sbJCxL1cwbt2oHhvXMLUSyQnlshDx384ynqsGfLcLGvcck7XStB1yuo\nPLdVJftHOEfKdgfPMtxaFbX1MCaTS03Mmk3FZSUXtxvBaApRgu7YSjFZKqLWVjCOwjkZzbummzxH\nj8c2Cp5VuKlCwUrd1RKiWraSbZRgjjtz07rwfdxaFdNqYDZXkJ0h2a27823IS7ZjuUwNMtfkBc+m\nimajN/dty4JTwqNqVZAS1Rlh9mckaGsddfEx8hu3ZybCv77/kv4YyZGBTXs+Sqw+K9V2em56MGT6\n0hbF4d9cgTolUGpl2VbazUjbo002Adg9xJzf4CguU6tM6C4F9FAkNYOK7PvCjARvYBvegX1w5Jst\njICopojrNgWShQ5uQxF2cgrHOUnFIdrKIFKU7wrcia3aOt3GeFUxWdPgaNxjm/YLuhp3YsgCQSpt\nPyqvb2YLmyRadpAzqcQd2/fvjTc1OtR4JwqZzNSsgk09FQ9yvF4ybzwYLdlX0kRNu43Td/llBUHc\ntNV7opAxTHxKwDR30TfvYl68zNEvLlM8yKn9pIee3T8Atdwi296huCvmhQ/ebp/8QgMjhB2bd7dR\n1RLTVog7tGka4Tjs/rJ9SBYONUXfp/H730e8+BQnz1ZY/uYuWRThrK0y3AxwRwb57ffQnmeJcJaR\nf+VFnL/4iR1jw5jldwI6lxw2ABH4BEcx3r02g1c3Kd3ok603MK4iCz0cbw0jxdysDnD43/4CftfQ\n+L96NL/vkvvGFm7MiHe81SBqLlO51qf2f3wP59wW08dbjC7kqIENNip37DsNcR2ihmKyKuh8cZPy\n/QgZpfjdhGSjirph9+l1E6arDq13DPUf2OqryZPLpAWXzktN2wh1rOk9pojrhjQMWb6dWAJ5dgXj\nSLxbbU7eXKf5/ojBBRtAeTd2yCcTnOMhQpeRqUY3a3SeqVC7NeXkSoGgq5F5gBECv68JD6a0X66i\nrrwIQOPdLqX3hpjAIwdyX6DDhx3e/F6OcGdFLmGIjnoIv2BbFFSstUEkKUYF4Cj01grakTi9iV1L\nTqvctCFtFfEOO9aE7jhQLs8LaOapwVzb115JaQM+KWxVYBja17bUyoh2h+TpM2jPkj3vvg1Kk7NL\ntmN6f2TVs5MeomLXVeIEI31bqQyQZhiw+9JmHkhKwNTKtgmo66HbJ2i1gUjttUvLHsG9E+RLKzYd\nvyHxTiaIc2c4fNNOupV2i/z969SefI3p+TrB7gjt2gIClRpq37hN8NwW2/UAZyzQ93dQK8scvuyQ\nnItm87XB5teHyChluFWg/taJrSZ+7jLHz/q4I0P5gaH0YMp0LaD0tffZ/UfPsVmpEOzbtOK5f2eD\nGlMKYTIhqksq2xmDLYeln0b4d48p1tcYryp6j/lkBcH6798gHwyY/rZ92WT/CUPQFhT2Zx3/rzSI\njz+rA+AnsSBRP2cobUc21VWtYCYTnA/u4oQBVMvkKzXSqq02MhL87w1tSWeWo1eayDCwkz6O5w/i\n/PAI2bf59+yU1MxIVFx37Uty45S8XkKWC7B7aCdn6COmMbp9ZKtKXAeSBFWpYM5vIO7OFvWZNG48\n1+b8947Jen1kEKCeumgJ1XBsF6IottUXq3VU6M+ldKPsS4E56SGkRDdrpK0CKjLoaUTYtr4umVsv\nSN7ro7SxPVVOO/p6DnnJR9759C7iH4e58+AT5EhHEc5Sc/6zc+EcuhBgHn2n3SNQzQa6PyA4ms57\ntDzcmPlcXqdTiI/5xB5FPhgg2aAbF+iPAkr3rWdgcE4Staw8Hx5av8ApTq6E8+j5tCTdHc3eXzfU\n+McxacW1XomxQ2FfUt5OyIqKtGgX9sF5yXTFepSCex7l+4bK3QnO8P9l701iNc3O+77fOeedvnm6\n81RzdVWPbDZ7ommRlGXJkizHNiJ5ALLwIgi8MAIHMZJFssvGQRAgmyBZZOEgsRN4jETLkqWIpElx\n6GY32aweq6trvPO93zy/wzlZPO/9qqq7RbcSb+j0AzTQhXvvN7zDeZ/zf/7DnKwcMl0NRTZ9DN7c\nMWsoxi+EEutw+nAUl5TBmyi8Y4/ikSMpQ1xTYvKZAkq8lgYXCkyXJbzYm+YSesT5uryfgYJ+ksuW\nVz0m84AyMEgL6FqIdYKeJSWNy20Uxr/+BQAqfyTnMOpYBjshy1ubMBwTHYak5QDd7pGOx7RfaWBm\nCnXjQxyw93dfYrIh1+nqj3IejXMcv1glGLmF/UVycQ1/bKm/cUTqHPriDpz2yE5OOH4+Yv2b+ejp\n2TpOSxgwnKGdOyTbS3SvGip/uI99/hIqdWSRwRlF4X6fR8Rmi4cHzYZ8hpJ5bKHvXg2I6wpvWqVo\nrpMURalZ3DWsf1cOau9Kge5TjtXvijqtcdOK0WHNxy4HxGXNvKZZf0N8oPa+ViIrZtS+8TZpvraE\nu/sULp7j4M+vsvEvd5ldXGa6qvBHmtrdGdnWMoOvn2e6pPEmju6VLfyRw71+g/RvviLn8doG3kYL\nN5xJzFBZzl3Uz/DvnZB98RwmEeQuOppTuZtx+lyZ9isJ5/5Zjg69/T56fY1ks47vX6FwGqOK6qEJ\n8dkIvj+RTV4UokoF7OFwkVmH1qQlDx2HEsodp3AqYzc3zhV1OsDrz7HdnnCVSgUoFwSZAmyzgto/\nlebbGEl28Dzhao4ni7gXZaXJ0plluBpQ6Dw8u2aeodIMOxyK5YJ14ry/XiW4fSL0idlc1tRHzEIB\nXCMfSc5i0mYJf6+DW6rjPuzifKFWgPgxDc6t408dYU/uK5Ti6BfXFrEv2YU17JNbVH7vbexTF5lc\nqJJG4gvntBKrhbKEbFdvDeDZqzz4WoXaLcdolqudMznmnZeWGV9MGDy3QunWHVScErUdUS+jsD9m\ndL7MZFlTvrxD6dCSDQYcf+VpQDZa84aTiLP+gKhrMTNH1LEkZY/k6TXislijeDNHZTfFXtnGRT7V\nn4j6Lui1JDpqRVG5lzvGB583Uf/elhnNFx5Abmt1Mffm+BTdNkQFgSzTjSaTrz9F4WiK2j1BtXvi\ndRIEuFoFdWVHdlP9Kao7wFVKuKcu4PUm8KEs/JW7AapUkDGeMaT1Iv68id0/hDyjTvmeGMttr5E0\nIsJ7HdRwCjmEnbUqZOUAMifhx0tNzMYq7B7ibt+HSkVudJ0T4iexcLDi5BP+S4BYLcQxurJNXPMW\nflQubwRVrQraYAcDsV0oy06Se/t4Ycjkl5+neKuziNX41FLqIQp0/QrujuTj2dnssR2/3T/EPXXp\nMdPLxypJxULhtRt83PRAlYrwKf5Tn1bZ0bGgYGff9VMsFNRUCMFJJyLqWmofDCgeR8yaPmlBEXUS\noqMJk205HtOWhw3yXLqPptjIYMYJOhaY20wTvP4Ub1Yi7EUUTxL8UYr19WO5Vd5IoROFN2UR5ZJW\nQtrPFJjXH3Ej98BGGbqaS7F3ZSGtfQClPQlM9seZIBw1n9GGtxjlWV8xqwePNVBBPw81BvyxpfzW\nPq4/oHRrlXitwmwpYlyXxvP+qIG7tkQWGoo3TxdkYC6eJ84bwrPRalxRrP2TW7iaBMsOL1UoHM1J\nDw7xtreIq4qtb4k5rKmKbPvCb+fxER8dM3tqm2CttSCdP1pBPxHTwxeewmqNVg04OWH7X+yTvfAU\nAMMdTeNmxqX/rbdww88iQ7Q3oPZRhGrWhQyvFN4kI7zxyXvEfPNNJr/yJdpPy/df+9708c8xkmOn\nrGN8oYI1CusryrsW70fSTMZf+iLl+4rs3ZsM/9KXadzM0IlIzrGW9EqF6v0UVSoy+pXrmBiu/3cH\npOPxYuRzFgTsTRyu10dnLbyxJilbrFH0r5QYr2lKh5bqrTHDiyUG5zSdv/UqzRv5Z33jFoQh0xfO\nY32x4dCjGdGJIVtvoiyE3QSvPUXFCcOnpemrvBfQuS6vYZ/9MhvfmeDv9WRMZjRuYh6ixYHGjUao\noCGWJY2aNCfOCYoOsNxgvOZL6PQHRyKUQUanKgoFdQp89FEHF4ViLZCbWp6ZbarQf2hnUKrjAp9k\npUKw38OttXC37kuGXpqhmw38gwGlgkd4Mlk0emfXlCoVJd6lEErjlzoJRC4UxFzXGBEaVeswj1GV\nEllJUNf5To3xqkfNa4mwIU2F/6TBP+xTNYrMl7DxNPfk0oMJ3rTG2u/cls9Rr3DvP48499cm4pBf\nvUZckY1J/faMeKVE5wmP6l2LvntA/xevkAWCCjbel987/lKZu7+1KjmbHUX3qqJarUKS0rzRp/1c\njcFOjWDgKJ5YTl+oU7kfE/+FFxcodHnXsXRDrBjU1Yv0L2umS5r6rZTCwZjpeonpiqJ+K6P2vXvY\n1SaDKxXq399drOXe7busfk8C6LNr50iqAXyM6vqz6vMm6ues5stFTCUkuHuCurcvHiW1Mm6thZrG\nuHYej/LWTQrPXmW6VqA4raN7osLAOdR0ju4OMGEgzrmpeMGY+x6UiosHivI81OayPFT7M7wTUebp\n5SXcUJLEs6s7OKPxD7qEuVJQBcHDaIF3PkLnDYnLx2FUShCGQqp8FBXKbTnM8jJ2+OlGZyo3+PR6\nE0rTRJzQfdA59yvNeSR6ewP6I7ILgsx5p0PS23dR9hyuGH7qa5/Vo5wpd39fXhuwH1Pt2dkMPc9I\nL67j8ZBwfsY9yQaDxbjorHSpJPEQ48knmqGP86QeRao+wVO7eonxEy1Kr93F9QfYSgSMUOWUWSMi\nK8go1imFP1JERxP0UYcod5kfbEuTEnUy/LtHYsTYqjPdrpIVNKoZEHRjvPaUWmxJSx7dJ6QxCnPO\ny9KNmWSe1YzwsDY1o82i8Jo0ZJGM1pKllLA+wxhpC5LEoHIBTJYfnqjviI6n6HmKawT4E+E0KOeI\nS1riQuai1DMzyfar3pCHE+0uabuDfu46NvTIAo3TbsFr+EJzl7dmNfzbh7g0I7uwhsos7s138V54\nOMr2zu8waykZKay2yCohOnN4vRkWmDy5Ju/fl38L6sQiUd4/bdP+q+eo7Hps/N+njC/W0aUSdjzG\nP+iRrNc5fWmJ5rsj3Os3SL7yBdJf+RL8/o/o/K1XAWi+n1J8MMa9fwv1wlPouwd47+xhV5sytrt7\nH3NhiaMvRWz9QQ+3uYw+/SS37sGf9wi6MsJNagGP4phxWeGPYdY0OCXO9aXdGb2rBdSOEJiTMpz/\nPw7IgPH5lLBjqN5LsJ6me73MrKXY/NaYbKPFeM0wazn6L6wTXVhisC7vFnUygt97neVqFQoR/sGA\n9e8Z8R7LHNVbY5rf6YLvMXx2BW9maX5g6Z/3WP+OfCd3YZO4VaT9pE/rHYs3y0NiV0PKN/uEfYvX\nn+NCw9FXGiQVRfVuxvCC5sWvvwfAj3a3SX4cAjUGFyLCnoXwIbqTBQo3m6POAs99D2sMuhBJrics\nmhhlWWTroZWEAOfxKq5WFvWwddijE5S3JkkOecaeZOIVRQDjGfCMoL1xrhotl4TX2bcyDrSW8GSC\n7k8WNA3vuC8k8TSPqOkOyC6sSbaelmBhun2Jf4nC3FHdkDVKTDZlg92+LsHR3SsRq//ygCwM84w6\nTbzdYLgV0vrhMfbeLumfe5bhpqHyxxOSEgsDV12ISOIy3rltsuUa/YsBTkNlLyONDP0Lfh5GLB5M\npcDAza8AACAASURBVN0Z/YslDn6xyfr/8hYAK1yk/UyZpKxIyzB/ZkLy/CX0t39M8ksvEIyseK3d\nn5GUPI5f1LRuxEzXCthQzkfYtyLKaDVRlTKFIxG77P6i5vJ/9g4RUA9fpnx3JBshYyiWxeV9ko/z\nwm4C33wTZjNmKwXK7x5j2mufuKf+pPq8ifo5qywSNZu3VEOr/OafJ7ntvyF5+hyASF37E4pxiu4N\ncUki0tszE8xGFVsMhVRZiTClAs4z2EYZsypNA7uHcHdPMvasRfk+TusFB8AOhpj378HWGulKjazk\nk4WGsD1bqOLcWg3/eAiHJ7hMFhi0Jn56Gz3bwHvvLqpcll3lNEGd5M3LM1eYrcpNP20Z0iJEXUf5\n3hTdn5I2iqQFg59lZAFkKzVUamFvX6DywEeFAXoujUq6VIHbUHj9o38rqRxYcKbseIxebv2Jv6ZH\nE3RvSHp0vPibR5ujT4wEJxPM5hocnnz8pXBb65iVJbKbH0mztbOBu/PgEw1U7z96lfavTvFvepy/\n00TVKqhJzHI0olydMluKmC+FFA4tQWfK8FKFpFzBXqsuUKS4BknVMdjxiI5a6ElMWiswr3sL+wMz\nNWRrJeKax7yqiasKlHCPQJqHpKhkEYxgup2iiinqNKB5Q+FPHUlBMW/7pJEv8TwW/ERGhwDeVIKD\ndewWikx/nDKvB1gfZi1RWwV9KJxaif4wgqwl6zKeSC43Ga8+QVIRG4Yz3lc8lebmQnjC20e9BZqU\nVANpjowhjR4SjO1Jm3PfKKOWl0laBdKCR9BP0ZMZankZnTgaNxPSeiQGe0tNWu/EhB05x7pRp3hk\nKe4KctC77FF6vQTjMfd+cwMzh7XvDTHtIa5aZVaXsNwWSBwMCPv4rQ9QYchsqUDxqEC6t49u1Rmv\naypA54mQpIwYcR4ek37s+rj991/l3O/GeN98k9lffJHoYPRYxmPp2NI/bxhdsJTvalbenDPejMhC\nmF7MzXpDhysX8La3qHzoUb0X449S5kshwdBS3svQ949way2qD1LimkfhNCZ40KV/QUjhh6/4XLh/\nVUx0U4v78A7+coW9r/psfNcQ3uuA79F/fpW0oGh9dx/X6TH+609hujISnJ1vsfv1ALSjvC+qO4Di\nP/shlEqc/JcFwl6ZsBsvRk1xWeMM3P4fxPX83P/5AwAGf/MVCicpSdnwtes32X/kmKhaFVcpyais\nGOShwIVF86J6Q0pHdXScLbL13GlHorGskzFclgnCGQa4bg9biTCT2YKkbvcPhXM6maBSEeoE/aKY\npnb7qEJB1osskyYq8OVaGY4kDw8ksSFO5DOkGS63ZrC1Ivo0X9e0ESL5bI7r9lFBwOnzVWZLcnwm\n51LUHQ9vAlmnKw7eTtzkRxsh43VF8bhBcTonrhhWfzhE+T7hwBG/LMfUH8Ys/X5E1qrQe6JE1LWS\nKBBbVOYIRsJ1HFyCpWsXmbdCGh8KmsllcRlPyz6ND6aMtiMGVxy0Q/x3bzP7pRe492s+T/xPJ5T+\n6UfMfuMl9r6qqVzpklRKBN0YrDwb5jVN+cVnyBSYO4e03p1x/HwBW0vFHf29++z9OUfxQY2tN8Qi\nwhvOufvX1nntb//3APyHf+U/Xqhz+xc9St8fcOn5z26Y/HkT9fNWCvxRKqjLulz8ejSTtG7AjB7Z\nOXUHsDfB+Z7A09Ytgi7d/VNUFKKbDWxFGii6fbkR18Xp113YRHeG4mXSqJJVIpzRuFaZuBFIlt0H\ne3B0ijerYnp55Mt0jskl97YYYSsR2qyiOn1suwPdLuFklem1NeF3JIJ0BF3wgkB2eklG/6K8xmTD\nsfWHMcG33kLXquJPE3gklRI4h5nLbD1rljFXLjLbqeNNM/zhREafgKoUsWH4mRqoj//O2Vjx09Ry\n2cHRolHyNjdw8/gTTumPlXNkNz/CVKsPORl52bffx1wWmbqKQnGaNp/Elbu/PmapOqH8bQ237sLW\nOnQHPBjXKQYJ8xyBUUmGHkxQrsJwS5LPs/BsuXAEXY0/djijSetFZqshSUlhPSh0LFnBEFckfkFl\njrAr4xSbrxrjFY0/zhuhDHTq4bRH2HOC2MSOsJtSv52RFjyJ7Yg0ysnPQV7LzB02yOcUx22Cg2NK\n6jLTFRlFpkVR76GgejfBH8bMmyF7X82JuhfHpHGGPg7Y/LYl6MZ0rxUxvrQOd+bibmyqVWyny6y1\nRf3HJ3D1IpXd+cNzOx7DT95l+pdfynkUUN5NFvyStGhwHhTfPoHzO2SNMoU7XbpfkteveJraN25g\nx2OG+S73DJ2crlka7yjIR7vmyaskJb3IEDRTeRhG+0NoNZl+YYfiOwcSpn1+h7geMbiasobYUIAn\nqFS99hDNfekZeY2rfbz/4l0AOtc8/FEBw8Mg8urre2TBFs33Lc44gsMhhy8vU9pzC8TFHynu/qU6\nlXs1mu8lojZMMhlT5tYVRa1h9whvuUjY9Rhuh6RX1h9aWRw6Dn+hhT+G1u+8K55dVwtEp4rwd18n\nefU5Dr9conhkafzzGzIKrFaZbCiyRik/LilRO8TMHKNNaaBKBxX8+4LwVX5YoPz2Lund++gXv4wz\n0uRvfjN+TH35S28P+R9/kHL+H8v1dmfQIsxjPbypoLBZOcR0RqjU4vLMSZdHuKiyIejMsAVvcU/a\n+RwdhrI5nExQiYyAXSWEbk8QpGKEyv2fzjydyDJBnMYT/MxKUoTnSTKDze9Po1GDsYwZC4VFiDS1\nChyfSoPX6YIf4O13iM8vS+Bxvnl0IGPFvIFrfzGj8lGeidcxtN5JmTWM5OsVItKCIwsVjfcmqKzI\neM1HJ6u0n1aUdw2uWqJwLPceCH8q6mbCV1rVlA4stY+m4scUJzjTADzM3JHWQuKqJupkxBXN6JJs\nfirvd3H39nDnniHoGMwMJi+e5/h5H1uNme3U8T9UFA6nFI4q9MpVlqdzXKAJe3LfhP2M/V+o0Hon\nIXjtBP+kQdCP0H2Pva8GbLJDeOLRei/F29pktlXH78+YbqdkeevkXr+xuE7Ke3K8RonwKT9Lfd5E\n/ZxVdDTF9CbQHaA3lkiaBWwtkMiH49OFRFcFklKvGnVsvYIr+JjDLlluDOmyTBbfXh+zvIzbWCJd\nq6EcixvZTGJcuYBdqYn8tDte5C+ZiUD2yjOkh6fosUQMKK0XIz0QHoDTvhAZp5Ktd+aZFB6OZffW\nG+KnGW44xEUhulohDcyCCG19hQ00ulgka3dQYYjJMoKcCOlPnOzahjM4PCGoFYUk6ZwsTIA9Pvkk\nifszKPQeLb3UQiXJ45l1j7zm2Sjxs5TLPbw+Xlnuw2JH408Q1r11gZiTTsTsj8vYHUfr5Dzu1l0h\n7ztFkmmUVQw3DePVGsrWSEqKuApmovBGsvgUThzN9yb4906wSzXiZkBS1MxaSqB9IzC3yjyCocVM\nM7yphBBPV6R5maxorC/qOZM41B7o2GIDzXDTkBY0zXaM//4ePhCcW6V/tcSsKX8H4I0doZX3y0oB\nZjzBOUdwPGbeqAnRWCuy6GHzprsj5hdLmCsCZ11fPeSt+xKbMq9poqOMwpGjuybX4F+qvclrT32J\n8LSOOeox3NHU/9UJ9so23vfekfORH2PleYzWxHZh+SddMYGtVbGby+jU4Q1TJk9vMFn2qN6ZogKf\n8n15wPlHfdLxGBWGFA5mFI4UvPQM5v17lB5oSofp4ppLawWmS4KYeBfPs7D32z8ifv4S02WPIOds\n9F5cJ+ymLL1u8C6ex9zv403lOoufv0Tw7i7Z0TH7X5WxUfTbeXbdxfOsvDGncy1k+ZuyKeKtAcnO\nEsWjGG8k72pv30fHy3gzu+BRQZ6f2M4ofu8m7twGg6tV2k+LelKnoLMdrFHEZU3jg3mORmULv67x\nesBoU1M6zsj6A/RTT1A8zSgd5aT5gkcawXBbU3vqIrx2AzZXCTsssuLiRsDa94bYwHD3Nwo448R3\n6tp5vP02xRNLstmE9QZJGRofZIzXzSJsGUTd+tagzs7/JdedP06JgvnimEcnElNlhjNcuSAGxiAE\n8Xwds0s14kZItDcSE8sklXXMZuhqhezkFD2eisHmcIJq1CUiphwusgsZTyHwyfoDTLOBnUxQcYxu\n1EVo4hncPF+bh6K+y/oDTCgb309Uvo660Qi/U5LpQOChlBJCfJLiwhA3naLnmtbbshZ2rgegZJND\nrYLrD7G1FOUMvatFuk/ChX8xQWUWZUPimo/pa8LvvrPwy7KXN9CJpXNdgqDjskS4ZLUIbMhowycc\nWMJuSueJiCxUTJc0ZiYoFUj2aeg2mNcU5QeCXMVVQ9gDdz9gtmSJalXcNCELQBVSDl8tEQzElgMQ\nn7qWEwQsDOk906R4mlH8JkyWZa3b/qMp/tv3sOsrZJGm/XSNsDnkC7//d+Tnf1nz4C/AhX+Sieeg\nNgxn4edN1L+vlZV85ktNCvd9dHtAsHskO5vcsuCszv7fLC+jRxNc7JNstWBnaZH15YwGrciSDJWJ\nV8wZogVgG2Vs6Al/xDekSxWcb/C6E3Q/l9kXIrxz2wvfk6xVwXoaM8kRscxJqOM4w9ZKqPoliFPc\n0SkaZIwXeOih7PzwPJKtFvNWKE6yQO2jFJU5pq9epXCnC55hulFh1vKpvCZZYFk5xNvviMLw9Rt4\nVy+Jp0reRH2qCs454V91u58p784Nhg93k39CfcJ+4E/6vdnscT7Yo5+p1fxUxMxV5MF57huO8F99\nH7O0JE3sbIa5uMMrS+/wj957gWAKKJis5kHKBkwM1buWym35fObeEaQpdn2F9nM10oIQtv2hjMvS\nUOP5mqCfE8ELhulqSBophtvyUJi3HDhIykbUNF1LNHaYOMUfG5RzQngdjcUbbJ5i5g4zcwuGrIlZ\njBiTio+3s0myWaN3KZRGywkPJWoL2jVd8VGuIU7FE+nE+nGBem1MZ+QTlw224JGUFaoo5/TPRBoT\nW/SHD8jmc5Z/vEbv157EH1uiNx6/Lrp/48Uc8YqxRR+jDXb/kGz9Gk6Dii1+HFMdJQS7HSbXVinc\nk8y6hTu+56F+8FPiX/kScSWk9pHH+neHpOUAb2tTxsSTmKhbIA0Vtlqk8I40TGmvz3ArpLwn1623\nvcW8pqn/4AgbrDN8doXyd26h372JefIqcaDp/rmL1P5pn81v5ajrjQ+xwN6vb4j3zRn95ywY+OYe\nR3/lMkk5ovVuQvj0ZYKBY7id21UAYVtT3nUUHwinZ7pWwps5Gh9Y/IkooAD8OCPqOLxRImPWowlp\nTR7ulTtTzDyifLMPTz2B7g0p3oF4pYS5fIGU3Cj1REa5VinYO2Ltj4OFYlTHFvP+PeIvPwEKln4C\nwb1TTn5xG/9imWCQMVsOaF/3CLtgEsfSjRnZRmuRJDD8MxeY/DeW6HdfI/6VL5GUPHaPlzjHgTS1\n1gq6A6iVJfG4yxGchVGmUcIvOmrLuK5ShFyh7MoF1GAo5HLA5URukhTd7uHqlfymFyWfLgovSpdL\n+bqdCXqUJAuV81mZlWXhmObrl4oTnHXCefI9mM6wiQSlYwxqnhuVxomsV0tNHLD5bUu0J5uOelBl\nsmSo3Z2LOWf+2mZmUSVN4Ti/N4czln5a5PRZnyUqRB86bL6B9LVGbS8TnfoUuhnWKCargTQhDqar\ninnDUAUKbYs/ykjKhsKpbKpALGTs05ep7Ga0n/SYbGV4U4OZOcq7kBQU01eu4k1Tlt9K6U4jwl4+\nrs93PWkk7ureKCZ78Tr9i5q1H4rxbvdKkfYzBda+dcrga1cYbZqFd537sMz578j6EPzea6yHr3Dw\nZY8scjSWL/NbF7/Jd4j4LPV5E/VzVn53hn9iUUdt0nxs5G1vSQxLatFduVHULJYFws9JjN0B/nSO\nrUl/rfsjGZv5nsDFcSwSW62wo7wRuAve2qogWSG4wMOMY1R3QJovUGdGnG40Fl+lvQN0li0WFIzB\nNOpCeEQgZlsK0atLecimFTVctUi63UDFVrynjvoLi4Nsdx+XphRz48q4ETHaDMhCqCA8ifJwhis+\nvOhVmmEDH/WIxPfhDxWmUsFOJp+pgfK2hGzrRqPF9/53Xo+gYovj//FfyflsxTs9Mucejg2VwvmG\nspkRRQnzkqN4AH4oDRQOdALezArSCDIW8AynLzYYnVOYmYw5ZJcoHk+9K3LOvAl4M4lkUY+Qa7KC\nRc8VcR2UVYDGmxoKR1PKe4q0ZJg3A/SffTL//JaonaKzh27BNlDM6jo3zIT5Vp3BuYC4KiRy8bdy\nlPekmdOJwymFzhzhR3K+7/lNspFP6Y5HMLKM10Kmz0945dw92sC3pppgry+WF0Bc8xic1+z8ducx\na4DRb75MUpYAXf8P38Db2iTLrw8dZ3hTzfBCgcqdqShNtSYpaYq5hD3r9TFPXhXe4c2P6F/waN2Y\nSkPc7jD7zZex/pqMRk8mlO/P8EYx6uCU9FxOcD84JCmz8KqaPLVOoWNJdpaIjibMVouLBrvzxSat\nb+/i7yyRvXid4K5cD2ccqf4zCWF9xtI/FP6IPUM2G1WmK4osdBw/77Pzrxwr3zrk3m+uk9XlXoit\nT3QjA6WYPLXOrGkoHiakUY483emDUsxWi4w2A5wOJTooKNO9euZGL9dO+a7BtIcymmQTu1lm+KxQ\nBoKBNMe9J6tEqy+gMkdaNkQneRM5TnFxLNFOHUX9g5EQ/DNH+d4EPUk4eaWBN4X13z9g+OwKWWgY\nXa8QvyRkffPrbdp3G1z5XQh+/0e4P/MF1Lt5Y+Mcs9Ui0dszdLWKC3x0oSCeTo9GuADhyUTQoumU\nbKOJMxrvxAryVK0I7eGsAUsEgbKdIeRkbFUswnQmSJbvCe/JD3Cby5AbotLu4dJUlLjzOarZkPif\njgiGbKuCOjxGGS1jZpBN9HSKKpfh4FiaLK0EqYoTlO9TfvtEnglA6b05hUZZ0PqcMqAHHt40xsSG\n+kcZSdXH6ytKDyYcvVSWcfvTlxch8QfPFUmLivK+KC39saXwxl3GL19guGUIeg/FH2mrLPYQmYPM\nLTy5dBgyXS6iMkdSdZiJJBY0341FMakVo3WPcKAp7s9YfSMhLXgkJb1YxyoPUiZrAXEzYrjl4Y+g\nfzGgdJix9v0xWcGDJGW0ISpRMR/WVO84wm+KN5sDTp9TLH/xkMnvrFFoJ3w0WQY+Xdz08fq8ifo5\nq+lGCTOzBEZhn9jE681wWSajN0+TropZ/Ww5YF4xFNophf0x6jiWpkvU+qhqFV2t4OIYOxjKA8Y5\nTL2GunZZfsnTuHmCK/g4BTq1qLt7pI+q9woF7FJNdl739xY8gQUMPp/LDZ4bzTnO/EhC9N1D1P09\n+V3fw3+A7LBKxRyKlr/JXnlaPHHGKWYSE93vobMaSclDhSGjTU3ze3NcMVoYapLkhPrpQ7RHl0qo\n9RUx4FxbxtWLMkJ4pD6hkPM8Md0DVLmMse4xHtNj9accDz5aOgzFePBTYmbOPgf5d8keiaoxraao\nfTKHrzKKQcLMF/SmvJeRFIUQnhZhuOkxq52B1GXJiFMQtkGnjsFl8AeawrHDnzqsL6RxbyJyeKcF\nNTrjvJTvGGwgYzZvIg/NuKrJwiImdszqRmTSkYwIC52MsBNTOHrYuqgkw8wiskgLmuFr/IkjzA09\nra8oHczxfihKK3VhW9yjo8pix6yyIt5MRoOTVS2+WIWYSSrX4DvzTezte8Rfew7/D98g7KZ4EyPC\nibPj+ORVZg1N68YU/d2fADKeNU9eFQuQ7ojjX1gn7DjMT29Bscjo5Qv4Y8l/BFAdD/aPFtfP0k8m\neL0JGTJam6wYrK+Ict8f/cdvoddWsf0B8yURhBSeu443EQTGW19j5ikq73WEj/jGO/hffR5Tr4k/\n2mlG+mCXwVe38CcO/d2H9hu6VKJ02wfnU/gX33v8YuoPiU5XWHl9wHSjhBpNcaWI0r6jtC/33PK3\n94QLGEXEV54j6mS0nw4Ju45wmEkeXWeC9TXTZbkmSkeZeIjlt4A3gcYHc9Q8k8gTIDs8wju/jDdO\nCe6eUNheIi15zJZ8uk8EBH25zsw051T6mmg+p/RgQhYKEmsDTTCy7H29QmnfkZRzxehpB1ghOhjh\nTSMOXpXzMumU2fndh91/53pBjETzsoHCNBti1WKU8JCaDWlu5jkSWw0JPzySjd9KC+Wge7VIaziH\n0w5uax3uPBBRi84FP56RBudM2ZfEuCxDpeKzRxSgnGNwqUL1xinTCw0KJ92FlYkqlxebz7NYJ2s0\n+gwNtxmqUhYy+1wiuux0JqpChGpB4Mu6cdrBnvG7fA8d+KjEkzVLG8xcoRKL9SExms41j3q5QenB\nBGccozVD6VbG6Io0nyaGpAL1n3aYr1VEjXtyQnF3mbRQYbhtON3UVG5HeP0po3NNGq8dSszWtoze\nWWlR+PE9qJTwnltnupGRZJqk6jHcMvgjR1xVZKGW0XjmCDoz5rXSIr6qeTRn9XUIunNmX6hQ2pPr\nE8DrTUhLVdR4Sv2jhOKtDvFmjclqRPX2QwTOfvV5sp0ZvrasfbtDslzEe3S3+G+pz5uon7PSsSWL\nNOTSaz06Iy+mqP0eOpfkVpoNStUiajKHdhd7aQsXnJcYlN1DssEAr1qBVgMdJ1DbwXka1R6i2jKe\nOEOTdJKKEiTwYX0Fs9TElSKcp3FTWWSyehFVuYQZCrHQlvNgzNlcYgdyQzo9mqDbPXnwJzkvyLrF\nz0lSnBXPkzPkwO82MBc3SSoBNjL4XSVoRGJxcUzUdtiTtixg+WKz8FXJYfkz4rDpj0Qh1x8yu9r6\nmYCtuXxBkLzcJwpjZAGdfNKe4NH3/NOUqVZlpNrrLxzaP63ORgCfqEZNvGhCw7I3ZKk45iRYEkJ2\nQRoK68t/SZlF8Ka4gnuifBs4dOYYo8SbKXGCWmWKYKgIhhlOK+Z1yc+bruQPhXwq542lSXNaMV1T\nYCFuWMK2IjqV8GB/IoRvM5qDUuieNKZuOKJ0UCS+uMx8KcBplfNWHOM1gz9xDyM15nOMUmSVEGVl\nTAAQdXNVVkUtHsLdvQofARscsewNcGkLG2hMvUZ3O6Cym5ENBuIGD+z98hIrP5os7AzSX3wB74/e\nQM1i7GoTNU9II1A1hR2P8VaXScqa6j//8UL5pgvRYw24+ektTv7aswRPN6n9mzs4IzyyqJPhPC2c\nGmOwsxnT1hl6U6F+a4p3MqT3lXMUThOy9z4k+/oXCbe36C8F+EtN3Ed3RY0KzJoaM8+EZE7ueXVh\nG28MS29/SmxQEBCMHGqe0T/vUXoPbOgRVxVB7r3FPEa9+AzDnWI+Ttyje2UH64tJon/Yl/yyiy+R\nhdD8IKVwOOXoL1bQ+TQqGDimKz6jzQbL/RH0+oLq5U2qq9fwH4BpVZnnRpClo5QsUhQ/kLFR95UN\n4r/xMmmoaLw/gR+/h/nacwT9mPZ1ydVTVjFbUsy/eJlZXVMZzxhfrxFX5bsU340ofPstbH6/OQ3V\nWyw2Pd4oT3OIQlRSkuzNJCUtBwSDszVohptOsaMx8XM7eNNM3juWuJGsEuIZg8sydK0ha4Fn5Pvm\nXnUup0o4a3HFkLQW4qcZ/ijDViIK9/PNab4mnqU72GpR1jbEJ5AkFeJ7UegT43Nlqm8e4AqhNFB5\niLJLMzHfHE8eixaSe9ehJjKKdLXywnIkGFm53/LLYLZawB9pCu0MjNhhAFQ/HJJWQ+ZrFZKqIfMV\n0fUrHL5Sw/qK1dcm9K4USGoRuhwwWdY0zja0+dqpjBZV8xFE7TX0S0N+7fy7/MH9V2m+O2fv6wF6\nDuUBzFZCJkua2u1YKAWiv6F4Kvl4xy9WmGxl7PyTY7Jbdzj6O19muLWEP4Zor0IWabJ6ET3L0Eku\nRMqPRXDzAO/eBR7Q4FLN4Z9MGKcB8NmoGZ83UT9n5Ywi6MZiRrlcwYVGnHZz2wBr5IES3e/B+7dh\nZxObh1eaiQTq2ifO5TfXXEYPmUX3xxLeOxwt3ksZ2UkRx1CIsLUig4uyINRvdFCHbWjWILVo5xZc\nK3mz3Nm2WcbkKJQNPNTt3QWSo5++hiv46O4INRxLE2W08KoCDzPMeQDtHuaggx4VIbPYe7uEF3dI\nVsroMB
gitextract_zm89e7wg/
├── Project_Proposal.md
├── README.md
├── _config.yml
├── models/
│ ├── Model1-CNNScratch.mlmodel
│ ├── Model1.mlmodel
│ └── mymodel-2.h5
├── notebooks/
│ └── CNN Layers Visualization.ipynb
└── src/
├── app.py
├── cnn_model.py
├── image_preparation.py
├── iphone_model.py
├── moleimages.py
├── templates/
│ ├── index.html
│ ├── predict.html
│ ├── predict_old.html
│ └── upload.html
├── test_model.py
├── top_vgg.py
├── train_model.new.py
├── train_model.py
├── train_model_DA.py
├── train_model_VGG_full.py
├── train_model_VGG_full_DA.py
└── train_model_VGG_top.py
SYMBOL INDEX (29 symbols across 9 files)
FILE: src/app.py
function allowed_file (line 18) | def allowed_file(filename):
function index (line 30) | def index():
function upload_file (line 34) | def upload_file():
function submit (line 62) | def submit():
function predict (line 66) | def predict(filename):
FILE: src/cnn_model.py
class CNN (line 8) | class CNN():
method __init__ (line 9) | def __init__(self, image_size=(128,128,3), nb_classes=2,
method architecture (line 26) | def architecture(self):
method fit (line 68) | def fit(self, X_train, y_train, X_test, y_test, nb_epoch=10, batch_siz...
method fit_generator (line 87) | def fit_generator(self, train_generator, validation_generator, n_samples,
method predict (line 105) | def predict(self, X):
method save_model (line 108) | def save_model(self, filename='model_save.h5'):
method load_model (line 112) | def load_model(self, filename):
FILE: src/image_preparation.py
function resize_images (line 7) | def resize_images():
function cv_images (line 18) | def cv_images(dir_b='data_scaled_validation/benign', dir_m='data_scaled_...
FILE: src/moleimages.py
class MoleImages (line 10) | class MoleImages():
method __init__ (line 11) | def __init__(self, dir=None):
method resize_bulk (line 15) | def resize_bulk(self, size=(128,128)):
method load_test_images (line 33) | def load_test_images(self, dir_b, dir_m):
method load_image (line 53) | def load_image(self, filename, size=(128,128)):
method save_h5 (line 61) | def save_h5(self, X, filename, dataset):
method load_h5 (line 73) | def load_h5(self, filename, dataset):
method save_png (line 82) | def save_png(self, matrix, dir, tag='img', format='png'):
FILE: src/test_model.py
function plot_roc (line 10) | def plot_roc(y_test, y_score, title='ROC Curve'):
FILE: src/top_vgg.py
function save_bottlebeck_features (line 21) | def save_bottlebeck_features():
function train_top_model (line 50) | def train_top_model():
FILE: src/train_model.new.py
function plot_roc (line 8) | def plot_roc(y_test, y_score, title='ROC Curve'):
FILE: src/train_model.py
function plot_roc (line 9) | def plot_roc(y_test, y_score, title='ROC Curve'):
FILE: src/train_model_DA.py
function plot_roc (line 10) | def plot_roc(y_test, y_score, title='ROC Curve'):
Condensed preview — 24 files, each showing path, character count, and a content snippet. Download the .json file or copy for the full structured content (4,179K chars).
[
{
"path": "Project_Proposal.md",
"chars": 5424,
"preview": "# Capstone Project Proposal\n#### *by David Soto* - dasoto@gmail.com\n@Galvanize Data Science Immersive Program\n## CNN to"
},
{
"path": "README.md",
"chars": 9630,
"preview": "# CNN to identify malign moles on skin\n#### *by David Soto* - dasoto@gmail.com\n@Galvanize Data Science Immersive Progra"
},
{
"path": "_config.yml",
"chars": 26,
"preview": "theme: jekyll-theme-cayman"
},
{
"path": "notebooks/CNN Layers Visualization.ipynb",
"chars": 4058340,
"preview": "{\n \"cells\": [\n {\n \"cell_type\": \"markdown\",\n \"metadata\": {},\n \"source\": [\n \"# CNN Layers Visualization for skin"
},
{
"path": "src/app.py",
"chars": 3347,
"preview": "import os\nfrom flask import Flask, request, render_template, redirect, url_for\nfrom flask import send_from_directory\nfro"
},
{
"path": "src/cnn_model.py",
"chars": 5343,
"preview": "from keras import optimizers\nfrom keras.models import Sequential, load_model\nfrom keras.layers import Conv2D, MaxPooling"
},
{
"path": "src/image_preparation.py",
"chars": 1282,
"preview": "from moleimages import MoleImages\nimport glob\nimport os\nimport numpy as np\n\n\ndef resize_images():\n print('Resizing Be"
},
{
"path": "src/iphone_model.py",
"chars": 1061,
"preview": "'''\nTo run this script you need to use Python 2.7\n'''\nfrom coremltools import converters\nfrom PIL import Image\nimport sy"
},
{
"path": "src/moleimages.py",
"chars": 3318,
"preview": "import numpy as np\nfrom skimage import io\nfrom skimage.transform import resize\n\nimport matplotlib.pyplot as plt\nimport g"
},
{
"path": "src/templates/index.html",
"chars": 9822,
"preview": "<!DOCTYPE html>\n<html lang=\"en\">\n\n <head>\n\n <meta charset=\"utf-8\">\n <meta name=\"viewport\" content=\"width=device-w"
},
{
"path": "src/templates/predict.html",
"chars": 4232,
"preview": "<!DOCTYPE html>\n<html lang=\"en\">\n\n <head>\n\n <meta charset=\"utf-8\">\n <meta name=\"viewport\" content=\"width=device-w"
},
{
"path": "src/templates/predict_old.html",
"chars": 1422,
"preview": "\n<!doctype html>\n<html lang=\"en\">\n <head>\n <title>Skin moles risk analyzer by David Soto</title>\n <!-- Required m"
},
{
"path": "src/templates/upload.html",
"chars": 210,
"preview": "<!doctype html>\n <title>Upload new File</title>\n <h1>Upload new File</h1>\n <form method=post enctype=multipart/form-d"
},
{
"path": "src/test_model.py",
"chars": 1395,
"preview": "from keras.preprocessing.image import ImageDataGenerator\nfrom keras.models import load_model\nfrom moleimages import Mole"
},
{
"path": "src/top_vgg.py",
"chars": 2557,
"preview": "import numpy as np\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.models import Sequential\nfrom ker"
},
{
"path": "src/train_model.new.py",
"chars": 2056,
"preview": "from keras.preprocessing.image import ImageDataGenerator\nfrom cnn_model import CNN\nfrom moleimages import MoleImages\nfro"
},
{
"path": "src/train_model.py",
"chars": 2064,
"preview": "from keras.preprocessing.image import ImageDataGenerator\nfrom cnn_model import CNN\nfrom moleimages import MoleImages\nfro"
},
{
"path": "src/train_model_DA.py",
"chars": 2519,
"preview": "from keras.preprocessing.image import ImageDataGenerator\nfrom keras.callbacks import EarlyStopping, ModelCheckpoint\nfrom"
},
{
"path": "src/train_model_VGG_full.py",
"chars": 3026,
"preview": "from keras.models import Model\nfrom keras import applications\nfrom keras.preprocessing.image import ImageDataGenerator\nf"
},
{
"path": "src/train_model_VGG_full_DA.py",
"chars": 2994,
"preview": "from keras.models import Model\nfrom keras import applications\nfrom keras.preprocessing.image import ImageDataGenerator\nf"
},
{
"path": "src/train_model_VGG_top.py",
"chars": 2683,
"preview": "from keras.models import Model\nfrom keras import applications\nfrom keras.preprocessing.image import ImageDataGenerator\nf"
}
]
// ... and 3 more files (download for full content)
About this extraction
This page contains the full source code of the dasoto/skincancer GitHub repository, extracted and formatted as plain text for AI agents and large language models (LLMs). The extraction includes 24 files (3.9 MB), approximately 1.0M tokens, and a symbol index with 29 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.