Upload 5 files

config.py

@@ -0,0 +1,5 @@
+TRAIN_DIR = "C:\\Users\\shrey\\Downloads\\ucf_dataset\\Train"
+TEST_DIR = "C:\\Users\\shrey\\Downloads\\ucf_dataset\\Test"
+DEVICE = "cuda"
+CLASSIFIER_TYPE = "mlp"  # Options: "logistic", "random_forest", "mlp"
+MODEL_SAVE_PATH = "saved_model.joblib"

label_encoder.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4efe2cb985d1d6f88344cad5d6c5a0120909dbd2fa24440578d2f19e12ab7c0e
+size 1055

model.py

@@ -0,0 +1,26 @@
+from sklearn.linear_model import LogisticRegression
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.neural_network import MLPClassifier
+from sklearn.metrics import classification_report
+import joblib
+from config import MODEL_SAVE_PATH
+
+def get_classifier(model_type):
+    if model_type == "logistic":
+        return LogisticRegression(max_iter=2000)
+    elif model_type == "random_forest":
+        return RandomForestClassifier(n_estimators=100)
+    elif model_type == "mlp":
+        return MLPClassifier(hidden_layer_sizes=(512, 256), max_iter=300)
+    else:
+        raise ValueError(f"Unknown model type: {model_type}")
+
+def train_classifier(X_train, y_train, model_type):
+    clf = get_classifier(model_type)
+    clf.fit(X_train, y_train)
+    joblib.dump(clf, MODEL_SAVE_PATH)
+    return clf
+
+def evaluate_classifier(model, X_test, y_test, label_encoder):
+    y_pred = model.predict(X_test)
+    print(classification_report(y_test, y_pred, target_names=label_encoder.classes_))

predict.py

@@ -0,0 +1,63 @@
+from PIL import Image
+import torch
+import joblib
+import numpy as np
+from transformers import CLIPProcessor, CLIPModel
+from config import DEVICE, MODEL_SAVE_PATH
+from flask import Flask, request, jsonify
+from flask_cors import CORS
+import os
+
+app = Flask(__name__)
+CORS(app)
+
+clip_model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32").to(DEVICE)
+clip_processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")
+
+def predict_image(image_path):
+    image = Image.open(image_path).convert("RGB")
+    inputs = clip_processor(images=image, return_tensors="pt").to(DEVICE)
+
+    with torch.no_grad():
+        image_features = clip_model.get_image_features(**inputs)
+        image_features = image_features / image_features.norm(p=2, dim=-1, keepdim=True)
+        features = image_features.cpu().numpy()
+
+    model = joblib.load(MODEL_SAVE_PATH)
+    label_encoder = joblib.load("label_encoder.joblib")
+    pred = model.predict(features)
+    label = label_encoder.inverse_transform(pred)
+    return label[0]
+
+@app.route('/predict', methods=['POST'])
+def predict():
+    if 'image' not in request.files:
+        return jsonify({'error': 'No image uploaded'}), 400
+
+    image = request.files['image']
+    if image.filename == '':
+        return jsonify({'error': 'No image selected'}), 400
+
+    try:
+        # Save the uploaded image temporarily
+        image_path = "temp_image.jpg"
+        image.save(image_path)
+
+        # Predict the image
+        prediction = predict_image(image_path)
+
+        # Remove the temporary image
+        os.remove(image_path)
+
+        return jsonify({'prediction': prediction})
+
+    except Exception as e:
+        return jsonify({'error': str(e)}), 500
+
+@app.route('/healthcheck', methods=['GET'])
+def healthcheck():
+    return jsonify({'status': 'ok'}), 200
+
+if __name__ == '__main__':
+    port = int(os.environ.get('PORT', 5000))
+    app.run(debug=True, host='0.0.0.0', port=port)

saved_model.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6989da95b96c941b3a5560d3d2c16b4bf4c16082059ccba58d8e418a0b9a8274
+size 6370936