from fastai.vision.all import *
import gradio as gr

def is_cat(x): return x[0].isupper() 

learn = load_learner('./image_model.pkl')

labels = learn.dls.vocab

def predict(img):
    img = PILImage.create(img)
    pred,pred_idx,probs = learn.predict(img)
    return {labels[i]: float(probs[i]) for i in range(len(labels))}

# All Gradio interfaces are created by constructing a gradio.Interface() object
# The Interface() object takes in the function that we want to make an 
# interface for (usually an ML model inference function)
# 'inputs' components (the number of input components should match 
# the number of parameters of the provided function)
# 'outputs' components (the number of output components should match 
# the number of values returned by the provided function)
title = "Dog Cat Classifier"
description = "A dog cat classifier trained on the Oxford Pets dataset with fastai. Created as a demo for Gradio and HuggingFace Spaces."
article="<p style='text-align: center'><a href='https://tmabraham.github.io/blog/gradio_hf_spaces_tutorial' target='_blank'>Blog post</a></p>"
examples = ['./cats_1.jpeg']
interpretation='default'
enable_queue=True

gr.Interface(
    fn=predict,
    inputs=gr.inputs.Image(shape=(512, 512)),
    outputs=gr.outputs.Label(num_top_classes=3),
    title=title,
    description=description,
    article=article,
    examples=examples,
    interpretation=interpretation,
    enable_queue=enable_queue).launch()