| from keras.models import load_model | |
| import numpy as np | |
| from keras.preprocessing import image | |
| import gradio as gr | |
| from PIL import Image | |
| def a(img): | |
| img = img.reshape( 64,64,3) | |
| model=load_model('./cats&dog.h5') | |
| test_image=np.expand_dims(img, axis=0) | |
| result=model.predict(test_image) | |
| if result[0][0]==1: | |
| prediction='Dog' | |
| print(prediction) | |
| return prediction | |
| else: | |
| prediction='Cat' | |
| print(prediction) | |
| return prediction | |
| input = gr.inputs.Image(type='pil', label="Original Image", source="upload", optional=True) | |
| inputs = [input] | |
| outputs = gr.outputs.Image(type="pil", label="Output Image") | |
| title = "Dog and Cat Object detection" | |
| image = gr.inputs.Image(shape=(64,64)) | |
| demo=gr.Interface(fn=a, inputs=image,examples=["photo/a01.jpg", "photo/a02.jpg","photo/a03.jpg","photo/a04.jpg"],title=title,outputs="text").launch(debug='True') | |
| if __name__ == "__main__": | |
| demo.launch() |