import gradio
from fastai.vision.all import *


def gradioeet(name):
    return "Hello " + name + "!!"


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


# path = untar_data(URLs.DOGS) / 'images'
# dls = ImageDataLoaders.from_name_func('.',
#                                       get_image_files(path), valid_pct=0.2, seed=42,
#                                       label_func=is_cat,
#                                       item_tfms=Resize(192))
#
# dls.valid.show_batch(max_n=4, nrows=1)
#

#
# learn = vision_learner(dls, resnet18, metrics=error_rate)
# learn.fine_tune(3)

# interp = ClassificationInterpretation.from_learner(learn)
# interp.plot_confusion_matrix()
#
# learn.export('model2.pkl')


learn = load_learner("model_last2.pkl")

categories = {"No_Cat", "Cat"}


def classify_image(img):
    pred, idx, probs = learn.predict(img)
    return dict(zip(categories, map(float, probs)))


image = gradio.Image(height=192, width=192)
label = gradio.Label()
examples = ["WX20240713-091831@2x.png", "WX20240713-091821@2x.png", "WX20240713-091430@2x.png",
            "WX20240713-090252@2x.png"]
intf = gradio.Interface(fn=classify_image, inputs=image, outputs=label, examples=examples)
intf.launch(inline=False)

# demo = gradio.Interface(fn=gradioeet, inputs="text", outputs="text")
# demo.launch(inline=False)