application file added

app.py

@@ -0,0 +1,36 @@
+import tensorflow as tf
+import numpy as np
+from PIL import Image
+import gradio as gr
+
+# CNN+LSTM model loaded
+model = tf.keras.models.load_model("model_9.h5")
+
+# Define the preprocessing function for the image
+def preprocess_image(image):
+    # Resize and normalize image to match model's expected input shape
+    image = image.resize((224, 224))  # Modify size based on your model
+    image_array = np.array(image) / 255.0  # Normalize
+    image_array = np.expand_dims(image_array, axis=0)  # Add batch dimension
+    return image_array
+
+# Define the function that generates a caption from the image
+def generate_caption(image):
+    preprocessed_image = preprocess_image(image)
+    
+    # Generate a caption from the model
+    # Note: Adjust this if your model requires a sequence start token or has a decoding loop
+    caption_tokens = model.predict(preprocessed_image)
+
+    return caption_tokens
+
+# Define the Gradio interface
+iface = gr.Interface(
+    fn=generate_caption,          # The function that generates captions
+    inputs=gr.inputs.Image(type="pil"),  # Accept an image input
+    outputs="text",                # Output a text caption
+    title="Image Captioning Model",
+    description="Upload an image, and the model will generate a caption describing it."
+)
+
+iface.launch()

model_9.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f851e1217ac2ccfe1166ff5848da48905b98c1883076d63a6b5d00871d4c49e
+size 16970992

requirements.txt

@@ -0,0 +1,4 @@
+tensorflow
+gradio
+pillow
+torch