File size: 1,291 Bytes
0cb8d44 7c8ef8f 0cb8d44 d10e834 0cb8d44 d10e834 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 |
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.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.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(share=True)
|