Datasets
Models
Downloads: 1
[fba4b6]:
/
WCEBleedGen.ipynb
319 lines (319 with data), 11.0 kB
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": [],
"authorship_tag": "ABX9TyOK/tfXqNBMTnLqQ6UmtznZ",
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/github/2004ARYAN/WCEBleedGen-AI/blob/main/WCEBleedGen.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"id": "6-HEO5ZZjkJl"
},
"outputs": [],
"source": [
"import zipfile"
]
},
{
"cell_type": "code",
"source": [
"# Path to the training dataset zip file\n",
"train_dataset_path = '/content/sample_data/WCEBleedGen.zip'\n",
"\n",
"# Path to the testing dataset zip file\n",
"test_dataset_path = '/content/sample_data/Auto-WCEBleedGen Challenge Test Dataset.zip'\n",
"\n",
"# Extract the training dataset\n",
"with zipfile.ZipFile(train_dataset_path, 'r') as zip_ref:\n",
" zip_ref.extractall('/content/sample_data')\n",
"\n",
"# Extract the testing dataset\n",
"with zipfile.ZipFile(test_dataset_path, 'r') as zip_ref:\n",
" zip_ref.extractall('/content/sample_data')"
],
"metadata": {
"id": "m5dvbzIJjnFn"
},
"execution_count": 2,
"outputs": []
},
{
"cell_type": "code",
"source": [
"# Organize the data directories\n",
"train_data_dir = '/content/sample_data/train_dataset'\n",
"test_data_dir = '/content/sample_data/test_dataset'\n"
],
"metadata": {
"id": "zqm-6MH9jnH7"
},
"execution_count": 3,
"outputs": []
},
{
"cell_type": "code",
"source": [
"import os\n",
"\n",
"# Set the path to the extracted training dataset directory\n",
"extracted_data_dir = '/content/sample_data/WCEBleedGen'\n",
"\n",
"# Define the path to your training and testing data within the extracted directory\n",
"train_data_dir = os.path.join(extracted_data_dir, '/content/sample_data/WCEBleedGen')\n",
"test_data_dir = os.path.join(extracted_data_dir, '/content/sample_data/Auto-WCEBleedGen Challenge Test Dataset')\n"
],
"metadata": {
"id": "LQ7GMenHjnM4"
},
"execution_count": 6,
"outputs": []
},
{
"cell_type": "code",
"source": [
"import tensorflow as tf\n",
"from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
"\n",
"\n",
"\n",
"# Create data generators for training and testing\n",
"train_datagen = ImageDataGenerator(rescale=1./255, validation_split=0.2)\n",
"train_generator = train_datagen.flow_from_directory(\n",
" train_data_dir,\n",
" target_size=(150, 150),\n",
" batch_size=32,\n",
" class_mode='binary',\n",
" subset='training' # For training data\n",
")\n",
"\n",
"validation_generator = train_datagen.flow_from_directory(\n",
" train_data_dir,\n",
" target_size=(150, 150),\n",
" batch_size=32,\n",
" class_mode='binary',\n",
" subset='validation' # For validation data\n",
")\n",
"\n",
"\n"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "l6dPYUqAjnPO",
"outputId": "8465f9e5-ce7f-4ed2-a637-9052bf110b2e"
},
"execution_count": 8,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Found 4190 images belonging to 2 classes.\n",
"Found 1046 images belonging to 2 classes.\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"import tensorflow as tf\n",
"from tensorflow.keras.models import Sequential\n",
"from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense\n",
"from tensorflow.keras.optimizers import Adam\n",
"\n",
"# Define and compile your model\n",
"model = Sequential([\n",
" Conv2D(32, (3, 3), activation='relu', input_shape=(150, 150, 3)),\n",
" MaxPooling2D(2, 2),\n",
" Conv2D(64, (3, 3), activation='relu'),\n",
" MaxPooling2D(2, 2),\n",
" Flatten(),\n",
" Dense(128, activation='relu'),\n",
" Dense(1, activation='sigmoid')\n",
"])\n",
"\n",
"model.compile(loss='binary_crossentropy', optimizer=Adam(lr=0.001), metrics=['accuracy'])\n",
"\n",
"# Train your model\n",
"history = model.fit(\n",
" train_generator,\n",
" steps_per_epoch=len(train_generator),\n",
" epochs=10,\n",
" validation_data=validation_generator,\n",
" validation_steps=len(validation_generator)\n",
")\n"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "b5DsWJjI1cao",
"outputId": "955fc3b8-8216-4220-f95d-5c5da2fbed28"
},
"execution_count": 9,
"outputs": [
{
"output_type": "stream",
"name": "stderr",
"text": [
"WARNING:absl:`lr` is deprecated in Keras optimizer, please use `learning_rate` or use the legacy optimizer, e.g.,tf.keras.optimizers.legacy.Adam.\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/10\n",
"131/131 [==============================] - 181s 1s/step - loss: 0.3123 - accuracy: 0.8814 - val_loss: 0.0428 - val_accuracy: 0.9895\n",
"Epoch 2/10\n",
"131/131 [==============================] - 160s 1s/step - loss: 0.0743 - accuracy: 0.9737 - val_loss: 0.0466 - val_accuracy: 0.9847\n",
"Epoch 3/10\n",
"131/131 [==============================] - 171s 1s/step - loss: 0.0316 - accuracy: 0.9883 - val_loss: 0.1191 - val_accuracy: 0.9713\n",
"Epoch 4/10\n",
"131/131 [==============================] - 158s 1s/step - loss: 0.0283 - accuracy: 0.9928 - val_loss: 0.1047 - val_accuracy: 0.9818\n",
"Epoch 5/10\n",
"131/131 [==============================] - 159s 1s/step - loss: 0.0123 - accuracy: 0.9976 - val_loss: 0.0974 - val_accuracy: 0.9837\n",
"Epoch 6/10\n",
"131/131 [==============================] - 161s 1s/step - loss: 0.0023 - accuracy: 0.9995 - val_loss: 0.1689 - val_accuracy: 0.9771\n",
"Epoch 7/10\n",
"131/131 [==============================] - 161s 1s/step - loss: 0.0018 - accuracy: 0.9998 - val_loss: 0.0591 - val_accuracy: 0.9895\n",
"Epoch 8/10\n",
"131/131 [==============================] - 159s 1s/step - loss: 0.0171 - accuracy: 0.9947 - val_loss: 0.0362 - val_accuracy: 0.9914\n",
"Epoch 9/10\n",
"131/131 [==============================] - 158s 1s/step - loss: 0.0045 - accuracy: 0.9986 - val_loss: 0.0446 - val_accuracy: 0.9914\n",
"Epoch 10/10\n",
"131/131 [==============================] - 169s 1s/step - loss: 0.0492 - accuracy: 0.9862 - val_loss: 0.0800 - val_accuracy: 0.9895\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"test_data_dir = '/content/sample_data/Auto-WCEBleedGen Challenge Test Dataset' # Update with the path to your testing dataset\n",
"test_datagen = ImageDataGenerator(rescale=1./255)\n",
"test_generator = test_datagen.flow_from_directory(\n",
" test_data_dir,\n",
" target_size=(150, 150),\n",
" batch_size=32,\n",
" class_mode='binary'\n",
")\n"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "-olZuu6R1cgV",
"outputId": "2fc323c3-5dbc-4864-d751-ed28aab4c1ce"
},
"execution_count": 11,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Found 564 images belonging to 2 classes.\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"predictions = model.predict(test_generator)\n"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "RkVc-2jA1ci8",
"outputId": "071bbfdd-1ea3-4b5f-d590-f30b62b40f85"
},
"execution_count": 12,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"18/18 [==============================] - 7s 385ms/step\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"import pandas as pd\n",
"import smtplib\n",
"\n",
"\n",
"# Step 1: Evaluation Metrics\n",
"# Calculate and gather evaluation metrics here\n",
"# Replace these with your actual evaluation metrics\n",
"accuracy = 0.95\n",
"recall = 0.90\n",
"f1_score = 0.92\n",
"iou = 0.80\n",
"ap = 0.85\n",
"map_score = 0.82\n",
"\n",
"# Step 2: Excel Sheet Preparation\n",
"# Create a pandas DataFrame with your testing results\n",
"# Replace these with your actual image IDs and predicted labels\n",
"image_ids = ['Image1', 'Image2', 'Image3', 'Image4', 'Image5']\n",
"predicted_labels = [1, 0, 1, 0, 1]\n",
"\n",
"results = {\n",
" 'Image name': image_ids,\n",
" 'Predicted class label': predicted_labels,\n",
" 'Predicted coordinates of bounding box': ['x1, y1, x2, y2'] * len(image_ids),\n",
" 'Confidence level': [0.95] * len(image_ids)\n",
"}\n",
"\n",
"df = pd.DataFrame(results)\n",
"\n",
"# Save the DataFrame to an Excel file\n",
"df.to_excel('auto_wce_bleedgen_results.xlsx', index=False)"
],
"metadata": {
"id": "28eA4pqs1clB"
},
"execution_count": 30,
"outputs": []
},
{
"cell_type": "code",
"source": [],
"metadata": {
"id": "z3Pgl-AX1cpK"
},
"execution_count": null,
"outputs": []
}
]
}