import torch
from PIL import Image
from torchvision import datasets, models, transforms
import gradio as gr
import os
import torch.nn as nn


os.system("wget https://github.com/liuxiaoyuyuyu/vanGogh-and-Other-Artist/blob/main/artist_classes.txt")
#os.system("wget https://github.com/liuxiaoyuyuyu/vanGogh-and-Other-Artist/blob/main/model_weights_mobilenet_v2_valp1trainp2.pth")

#model = torch.hub.load('pytorch/vision:v0.9.0', 'mobilenet_v2', pretrained=False)
#checkpoint = 'https://github.com/liuxiaoyuyuyu/vanGogh-and-Other-Artist/blob/main/model_weights_mobilenet_v2_valp1trainp2.pth'
#model.load_state_dict(torch.hub.load_state_dict_from_url(checkpoint, progress=False))
model = models.mobilenet_v2()
num_ftrs = model.classifier[1].in_features
model.classifier[1] = nn.Linear(num_ftrs, 6)
#model = model.to(device)
model.load_state_dict(torch.load('model_weights_mobilenet_v2_valp1trainp2.pth'))

#torch.hub.download_url_to_file("https://github.com/pytorch/hub/raw/master/images/dog.jpg", "dog.jpg")


def inference(input_image):
    preprocess = transforms.Compose([
        transforms.Resize(256),
        transforms.CenterCrop(224),
        transforms.ToTensor(),
        transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
    ])
    input_tensor = preprocess(input_image)
    input_batch = input_tensor.unsqueeze(0) # create a mini-batch as expected by the model

    # move the input and model to GPU for speed if available
    if torch.cuda.is_available():
        input_batch = input_batch.to('cuda')
        model.to('cuda')

    with torch.no_grad():
        output = model(input_batch)
    # The output has unnormalized scores. To get probabilities, you can run a softmax on it.
    probabilities = torch.nn.functional.softmax(output[0], dim=0)

    # Read the categories
    with open("artist_classes.txt", "r") as f:
        categories = [s.strip() for s in f.readlines()]
    # Show top categories per image
    top5_prob, top5_catid = torch.topk(probabilities, 6)
    result = {}
    for i in range(top5_prob.size(0)):
        result[categories[top5_catid[i]]] = top5_prob[i].item()
    return result

inputs = gr.inputs.Image(type='pil')
outputs = gr.outputs.Label(type="confidences",num_top_classes=5)

title = "MOBILENET V2"
description = "Gradio demo for MOBILENET V2, Efficient networks optimized for speed and memory, with residual blocks. To use it, simply upload your image, or click one of the examples to load them. Read more at the links below."
article = "<p style='text-align: center'><a href='https://arxiv.org/abs/1801.04381'>MobileNetV2: Inverted Residuals and Linear Bottlenecks</a> | <a href='https://github.com/pytorch/vision/blob/master/torchvision/models/mobilenet.py'>Github Repo</a></p>"

#examples = [
#            ['dog.jpg']
#]
#gr.Interface(inference, inputs, outputs, title=title, description=description, article=article, examples=examples, analytics_enabled=False).launch()
gr.Interface(inference, inputs, outputs, title=title, description=description, article=article, analytics_enabled=False).launch()