Upload 23 files

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+static/bgpo.jpeg filter=lfs diff=lfs merge=lfs -text
+static/cat.jpg filter=lfs diff=lfs merge=lfs -text
+static/fish.jpg filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,207 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/

app.py

@@ -0,0 +1,71 @@
+from flask import Flask, render_template, request
+from tensorflow.keras.models import load_model
+from tensorflow.keras.preprocessing import image
+import numpy as np
+import os
+import uuid
+import tensorflow as tf
+import random
+
+# Fix randomness for reproducibility
+os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
+tf.random.set_seed(42)
+np.random.seed(42)
+random.seed(42)
+
+app = Flask(__name__)
+
+# Load the model (only one model now)
+model = load_model("model/cat_dog_neither_classifier_new.h5", compile=False)
+  # <-- your model file
+
+class_names = ['cat', 'dog', 'neither']
+UPLOAD_FOLDER = 'static/uploads'
+os.makedirs(UPLOAD_FOLDER, exist_ok=True)
+
+def preprocess_image(img_path):
+    img = image.load_img(img_path, target_size=(224, 224))  # Ensure matches model input
+    img_array = image.img_to_array(img) / 255.0
+    img_array = np.expand_dims(img_array, axis=0)
+    return img_array
+
+@app.route('/', methods=['GET'])
+def index():
+    return render_template('upload.html')
+
+@app.route('/predict', methods=['POST'])
+def predict():
+    if 'file' not in request.files:
+        return "No file part", 400
+
+    file = request.files['file']
+    if file.filename == '':
+        return "No selected file", 400
+
+    filename = str(uuid.uuid4()) + os.path.splitext(file.filename)[1]
+    img_path = os.path.join(UPLOAD_FOLDER, filename)
+    file.save(img_path)
+
+    # Preprocess image
+    processed = preprocess_image(img_path)
+
+    # Predict
+    prediction = model.predict(processed)[0]
+    prediction /= np.sum(prediction)  # normalize
+
+    class_index = int(np.argmax(prediction))
+    confidence = round(float(np.max(prediction)) * 100, 2)
+    final_class = class_names[class_index]
+
+    return render_template(
+        'result.html',
+        prediction=final_class,
+        confidence=confidence,
+        img_path='/' + img_path
+    )
+
+if __name__ == '__main__':
+    import os
+    port = int(os.environ.get("PORT", 5000))  # Render sets PORT
+    app.run(host='0.0.0.0', port=port, debug=False)
+

main.py

@@ -0,0 +1,80 @@
+import tensorflow as tf
+from tensorflow.keras.models import Model
+from tensorflow.keras.layers import Dense, Dropout, GlobalAveragePooling2D
+from tensorflow.keras.preprocessing import image_dataset_from_directory
+from tensorflow.keras.applications import MobileNetV2
+from tensorflow.keras.applications.mobilenet_v2 import preprocess_input
+from tensorflow.keras.layers import RandomFlip, RandomRotation, RandomZoom
+from tensorflow.keras.callbacks import EarlyStopping, ReduceLROnPlateau
+import os
+
+# Constants
+img_size = 224
+batch_size = 32
+epochs = 30  # Increased epochs for deeper training
+
+# Callbacks
+early_stop = EarlyStopping(monitor='val_accuracy', patience=5, restore_best_weights=True)
+lr_reduce = ReduceLROnPlateau(monitor='val_loss', factor=0.5, patience=3, verbose=1, min_lr=1e-6)
+
+# Load datasets
+train_dataset = image_dataset_from_directory(
+    'dataset/training_set',
+    labels='inferred',
+    label_mode='categorical',
+    image_size=(img_size, img_size),
+    batch_size=batch_size,
+    shuffle=True
+)
+
+test_dataset = image_dataset_from_directory(
+    'dataset/test_set',
+    labels='inferred',
+    label_mode='categorical',
+    image_size=(img_size, img_size),
+    batch_size=batch_size
+)
+
+class_names = train_dataset.class_names
+print("Class indices:", class_names)
+
+# Preprocessing
+train_dataset = train_dataset.map(lambda x, y: (preprocess_input(x), y)).prefetch(tf.data.AUTOTUNE)
+test_dataset = test_dataset.map(lambda x, y: (preprocess_input(x), y)).prefetch(tf.data.AUTOTUNE)
+
+# Data Augmentation
+data_augmentation = tf.keras.Sequential([
+    RandomFlip('horizontal'),
+    RandomRotation(0.2),
+    RandomZoom(0.2),
+])
+
+# Load pretrained base model
+base_model = MobileNetV2(input_shape=(img_size, img_size, 3), include_top=False, weights='imagenet')
+base_model.trainable = False  # Freeze base layers
+
+# Build model
+inputs = tf.keras.Input(shape=(img_size, img_size, 3))
+x = data_augmentation(inputs)
+x = base_model(x, training=False)
+x = GlobalAveragePooling2D()(x)
+x = Dropout(0.3)(x)
+outputs = Dense(3, activation='softmax')(x)  # 3 classes: cat, dog, neither
+
+model = Model(inputs, outputs)
+
+# Compile
+model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
+model.summary()
+
+# Train
+history = model.fit(
+    train_dataset,
+    validation_data=test_dataset,
+    epochs=epochs,
+    callbacks=[early_stop, lr_reduce]
+)
+
+model.save('cat_dog_neither_classifier_new.h5', save_format='h5')
+print("✅ Training complete and model saved as .h5.")
+

model/cat_dog_neither_classifier_new.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67926b9d15446d349fbfc3f9150e3a71ba7c59b62f3532ab6dbd36cc7b51df90
+size 9392928

render.yaml

@@ -0,0 +1,8 @@
+
+services:
+  - type: web
+    name: cat-dog-classifier
+    env: python
+    buildCommand: pip install -r requirements.txt
+    startCommand: python app.py
+    pythonVersion: 3.10.13

requirements.txt

@@ -0,0 +1,6 @@
+Flask==2.3.3
+tensorflow==2.15.0
+numpy==1.24.3
+Pillow==10.0.1
+
+

runtime.txt

@@ -0,0 +1 @@
+python-3.10.13

static/style.css

@@ -0,0 +1,216 @@
+body {
+    background: url("/static/bgpo.jpeg") no-repeat center center fixed;
+    background-size: cover;
+    color: #060721;
+    font-family: 'Segoe UI', sans-serif;
+    display: flex;
+    justify-content: center;
+    align-items: center;
+    height: 100vh;
+    flex-direction: column;
+    margin: 0;
+}
+
+h1{
+    font-size: 32px;
+    color: #0d333f;
+    font-family: "Segoe UI", sans-serif;
+    text-align: center;
+    margin-bottom: 3px;
+}
+h2 {
+    font-size: 20px;
+    color: #33a6cc;
+    font-family: "Segoe UI", sans-serif;
+    margin-bottom: 20px;
+}
+
+.upload-box {
+    background-color: #dafffc2a;
+    border-radius: 15px;
+    padding: 40px 30px;
+    backdrop-filter: blur(3px);
+    -webkit-backdrop-filter: blur(3px);
+    display: inline-block;
+    box-shadow: 0 0 20px rgba(90, 90, 255, 0.3);
+    max-width: 500px;
+    width: 100%;
+    border: none;
+    border-radius: 25px;
+    border-color: 2px, #e2fdff;
+}
+
+.drop-area {
+    border: 2px dashed #61ddff;
+    padding: 40px 20px;
+    border-radius: 12px;
+    display: block;
+    cursor: pointer;
+    transition: 0.3s;
+    text-align: center;
+    box-shadow: 0 0 10px #a0ccff88;
+}
+
+.drop-area:hover {
+    background: #ffe8b62f;
+    box-shadow: 0 0 10px #58a6ff88;
+}
+
+.drop-area p {
+    font-size: 16px;
+    margin-bottom: 20px;
+    color: rgba(46, 46, 46, 0.927);
+    font-weight: 600;
+}
+
+input[type="file"] {
+    display: none;
+}
+
+.upload-btn {
+    padding: 12px 25px;
+    border: none;
+    border-radius: 25px;
+    background: linear-gradient(to right, #3b82f6, #06b6d4);
+    color: white;
+    font-weight: bold;
+    cursor: pointer;
+    font-size: 16px;
+    transition: 0.3s ease;
+    box-shadow: 0 0 15px #3b82f688;
+    margin-top: 20px;
+}
+
+.upload-btn:hover {
+    transform: scale(1.05);
+    box-shadow: 0 0 25px #3b82f6aa;
+}
+
+.note {
+    font-size: 14px;
+    margin-top: 25px;
+    color: #575757;
+    text-align: center;
+}
+
+.note span {
+    background: #21262d;
+    padding: 5px 10px;
+    border-radius: 8px;
+    margin: 0 5px;
+    color: #58a6ff;
+    font-weight: bold;
+    font-size: 13px;
+}
+
+.sample-images {
+    display: flex;
+    justify-content: center;
+    gap: 15px;
+    margin-top: 15px;
+}
+
+.sample-images img {
+    width: 80px;
+    height: 80px;
+    object-fit: cover;
+    border-radius: 10px;
+    box-shadow: 0 0 10px rgba(0,0,0,0.2);
+    cursor: pointer;
+    border: 1px #d9efff solid;
+    box-shadow: #00395d88;
+}
+
+/* Reset + Base */
+.result-body {
+    margin: 0;
+    padding: 0;
+    font-family: 'Segoe UI', sans-serif;
+    background: #ffffff;
+    color: #0d1b2a;
+    display: flex;
+    justify-content: center;
+    align-items: center;
+    min-height: 100vh;
+}
+
+/* Main Container */
+.container {
+    text-align: center;
+    max-width: 500px;
+    width: 90%;
+    padding: 30px 25px;
+    background: rgba(255, 255, 255, 0.85);
+    border-radius: 20px;
+    box-shadow: 0 8px 30px rgba(0, 170, 255, 0.15);
+    backdrop-filter: blur(8px);
+}
+
+/* Glowing Heading */
+.glow-heading {
+    font-size: 1.9rem;
+    color: #00395d;
+    text-shadow: 0 0 5px rgba(0, 170, 255, 0.3);
+    margin-bottom: 25px;
+}
+
+/* Image Preview */
+.preview-img {
+    width: 100%;
+    max-height: 300px;
+    object-fit: contain;
+    border-radius: 12px;
+    border: 2px dashed #00bfff;
+    padding: 8px;
+    background: #f0faff;
+    box-shadow: 0 4px 20px rgba(0, 170, 255, 0.1);
+}
+
+/* Card Box */
+.card-glow {
+    background: #f9fdff;
+    border-radius: 15px;
+    padding: 20px;
+    margin-top: 15px;
+    border: 1px solid #cceeff;
+    box-shadow: 0 0 10px rgba(0, 170, 255, 0.1);
+}
+
+/* Result Text */
+.result-info {
+    margin-top: 15px;
+    font-size: 1rem;
+    color: #002b4a;
+}
+
+.highlight {
+    color: #ff4081;
+    font-weight: bold;
+    text-shadow: 0 0 3px rgba(255, 64, 129, 0.2);
+}
+
+.confidence {
+    color: #ffa500;
+    font-weight: bold;
+    text-shadow: 0 0 3px rgba(255, 165, 0, 0.2);
+}
+
+/* Glowing Button */
+.glow-button {
+    display: inline-block;
+    margin-top: 30px;
+    padding: 12px 30px;
+    background: linear-gradient(145deg, #00cfff, #00aaff);
+    color: #fff;
+    border: none;
+    border-radius: 30px;
+    text-decoration: none;
+    font-weight: 600;
+    box-shadow: 0 5px 15px rgba(0, 170, 255, 0.3);
+    transition: all 0.3s ease-in-out;
+}
+
+.glow-button:hover {
+    background: #009fe3;
+    box-shadow: 0 8px 20px rgba(0, 170, 255, 0.5);
+}

templates/result.html

@@ -0,0 +1,23 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <title>Prediction Result</title>
+    <link rel="stylesheet" type="text/css" href="{{ url_for('static', filename='style.css') }}">
+</head>
+<body class="result-body">
+    <div class="container">
+        <h1 class="glow-heading">🐾 Prediction Result</h1>
+
+        <div class="card-glow">
+            <img src="{{ img_path }}" alt="Uploaded Image" class="preview-img">
+            <div class="result-info">
+                <p><strong>Prediction:</strong> <span class="highlight">{{ prediction }}</span></p>
+                <p><strong>Confidence:</strong> <span class="confidence">{{ confidence }}%</span></p>
+            </div>
+        </div>
+
+        <a href="/" class="glow-button">🔁 Classify Another Image</a>
+    </div>
+</body>
+</html>

templates/upload.html

@@ -0,0 +1,67 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <title>Upload Image</title>
+    <h1>Cat, Dog or Neither?</h1>
+    <link rel="stylesheet" href="{{ url_for('static', filename='style.css') }}">
+</head>
+<body>
+    <h2>Upload an Image</h2>
+    <div class="upload-box">
+
+        <form id="upload-form" method="POST" action="/predict" enctype="multipart/form-data">
+            <div class="drop-area" id="drop-area">
+                <p>Drag or drop images here or click to select</p>
+                <input type="file" name="file" id="file-input" accept="image/*">
+            </div>
+            <button class="upload-btn" type="submit">Upload</button>
+        </form>
+
+        
+    </div>
+<div class="note">Try these sample images:</div>
+        <div class="sample-images">
+            <img src="/static/cat.jpg" alt="Cat">
+            <img src="/static/dog.webp" alt="Dog">
+            <img src="/static/horse.webp" alt="Other">
+            <img src="/static/fish.jpg" alt="Other">
+        </div>
+    <script>
+        const dropArea = document.getElementById('drop-area');
+        const fileInput = document.getElementById('file-input');
+        const form = document.getElementById('upload-form');
+
+        // When file is selected via click
+        fileInput.addEventListener('change', () => {
+            if (fileInput.files.length > 0) {
+                form.submit();
+            }
+        });
+
+        // Click on drag area triggers file input
+        dropArea.addEventListener('click', () => {
+            fileInput.click();
+        });
+
+        // Handle drag-and-drop
+        dropArea.addEventListener('dragover', (e) => {
+            e.preventDefault();
+            dropArea.style.backgroundColor = "#dbf9ff3d";
+        });
+
+        dropArea.addEventListener('dragleave', () => {
+            dropArea.style.backgroundColor = "";
+        });
+
+        dropArea.addEventListener('drop', (e) => {
+            e.preventDefault();
+            dropArea.style.backgroundColor = "";
+            if (e.dataTransfer.files.length > 0) {
+                fileInput.files = e.dataTransfer.files;
+                form.submit(); // 🚀 Submit form automatically
+            }
+        });
+    </script>
+</body>
+</html>

utils/evaluate.py

@@ -0,0 +1,22 @@
+from tensorflow.keras.models import load_model
+from tensorflow.keras.preprocessing import image_dataset_from_directory
+import tensorflow as tf
+
+# Load model
+model = load_model('model/cat_dog_neither_classifier_new.h5')  # Updated filename
+
+# Load test data
+test_dataset = image_dataset_from_directory(
+    'dataset/test_set',
+    labels='inferred',
+    label_mode='categorical',
+    image_size=(224, 224),
+    batch_size=32
+)
+
+# Normalize & prefetch
+test_dataset = test_dataset.map(lambda x, y: (x / 255.0, y)).prefetch(tf.data.AUTOTUNE)
+
+# Evaluate
+loss, accuracy = model.evaluate(test_dataset)
+print(f"Test Accuracy: {accuracy:.4f}")

utils/predict.py

@@ -0,0 +1,36 @@
+import os
+import numpy as np
+from tensorflow.keras.models import load_model
+from tensorflow.keras.preprocessing import image
+
+from tensorflow.keras.models import load_model
+
+# Load your old model
+model = load_model("model/cat_dog_neither_classifier_new.h5", compile=False)
+
+# Class names — must match the order used during training
+class_names = ['cat', 'dog', 'neither']
+
+def preprocess_image(image_path):
+    img = image.load_img(image_path, target_size=(224, 224))  # ✅ Match model input
+    img_array = image.img_to_array(img) / 255.0
+    img_array = np.expand_dims(img_array, axis=0)
+    return img_array
+
+def predict_image(image_path):
+    if not os.path.exists(image_path):
+        raise FileNotFoundError(f"Image not found: {image_path}")
+
+    processed_img = preprocess_image(image_path)
+    prediction = model.predict(processed_img)[0]
+
+    prediction /= np.sum(prediction)  # Normalize
+    class_index = np.argmax(prediction)
+    confidence = float(np.max(prediction))
+
+    return class_names[class_index], round(confidence * 100, 2)
+
+if __name__ == "__main__":
+    image_path = "dog.webp"  # You can replace this with a path from CLI
+    label, confidence = predict_image(image_path)
+    print(f"Prediction: {label} ({confidence}%)")