Update app.py

app.py

@@ -4,7 +4,7 @@ from tensorflow.keras.applications import EfficientNetB0, ResNet50
 from tensorflow.keras.applications.efficientnet import preprocess_input as efficient_preprocess
 from tensorflow.keras.applications.resnet import preprocess_input as resnet_preprocess
 from tensorflow.keras.preprocessing import image
-from tensorflow.keras.layers import Dense, GlobalAveragePooling2D
+from tensorflow.keras.layers import Input, Dense, GlobalAveragePooling2D
 from tensorflow.keras.models import Model
 import numpy as np
 
@@ -13,10 +13,13 @@ IMG_SIZE = 224
 MODEL_TYPE = "efficientnet"  # or "resnet"
 CLASS_NAMES = ['Cat', 'Dog', 'Panda']  # Replace with your actual classes
 
+# ✅ Input Tensor
+input_tensor = Input(shape=(IMG_SIZE, IMG_SIZE, 3))
+
 # ✅ Load Base Model
-base_model = EfficientNetB0(weights='imagenet', include_top=False, input_shape=(IMG_SIZE, IMG_SIZE, 3)) \
+base_model = EfficientNetB0(weights='imagenet', include_top=False, input_tensor=input_tensor) \
              if MODEL_TYPE == "efficientnet" else \
-             ResNet50(weights='imagenet', include_top=False, input_shape=(IMG_SIZE, IMG_SIZE, 3))
+             ResNet50(weights='imagenet', include_top=False, input_tensor=input_tensor)
 base_model.trainable = False
 
 # ✅ Build Classifier
@@ -28,7 +31,7 @@ model = Model(inputs=base_model.input, outputs=output)
 # ✅ Compile & Load Weights (Optional)
 model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
 try:
-    model.load_weights("your_weights.h5")  # Optional: load pretrained weights
+    model.load_weights("your_weights.h5")
 except Exception as e:
     print("⚠️ Could not load weights:", e)