import torch
from PIL import Image
from torchvision import transforms
import gradio as gr
import os
# list of models: 'mealv1_resnest50', 'mealv2_resnest50', 'mealv2_resnest50_cutmix', 'mealv2_resnest50_380x380', 'mealv2_mobilenetv3_small_075', 'mealv2_mobilenetv3_small_100', 'mealv2_mobilenet_v3_large_100', 'mealv2_efficientnet_b0'
# load pretrained models, using "mealv2_resnest50_cutmix" as an example
model = torch.hub.load('AK391/MEAL-V2','meal_v2', 'mealv2_resnest50_cutmix', pretrained=True)
model.eval()
# Download an example image from the pytorch website
torch.hub.download_url_to_file("https://github.com/pytorch/hub/raw/master/images/dog.jpg", "dog.jpg")

# Download ImageNet labels
os.system("wget https://raw.githubusercontent.com/pytorch/hub/master/imagenet_classes.txt")

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("imagenet_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, 5)
    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 = "MEAL_V2"
description = "Gradio demo for MEAL_V2, Boosting Tiny and Efficient Models using Knowledge Distillation. 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/2009.08453'>MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks</a> | <a href='https://github.com/szq0214/MEAL-V2'>Github Repo</a></p>"

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