import torch, torchvision
from torchvision import transforms
import numpy as np
import gradio as gr
from PIL import Image
from pytorch_grad_cam import GradCAM
from pytorch_grad_cam.utils.image import show_cam_on_image
from custom_resnet import Net
from PIL import Image
import io

model = Net('batch')
model.load_state_dict(torch.load("model.pth", map_location=torch.device('cpu')), strict=False)

classes = ('plane', 'car', 'bird', 'cat', 'deer',
           'dog', 'frog', 'horse', 'ship', 'truck')

def inference(input_img_files, transparency = 0.5, target_layer_number = -1):
    confidences_list = []
    visualizations_list = []
    
    for input_img_file in input_img_files:
        # Convert the temporary file wrapper to a PIL Image
        with open(input_img_file.name, "rb") as f:
            input_img = Image.open(io.BytesIO(f.read())).convert("RGB")
        transform = transforms.ToTensor()
        org_img = input_img
        input_img = transform(input_img)
        # input_img = input_img
        input_img = input_img.unsqueeze(0)
        outputs = model(input_img)
        softmax = torch.nn.Softmax(dim=0)
        o = softmax(outputs.flatten())
        confidences = {classes[i]: float(o[i]) for i in range(10)}
        confidences_list.append(confidences)

        _, prediction = torch.max(outputs, 1)
        target_layers = [model.layer2[target_layer_number]]
        cam = GradCAM(model=model, target_layers=target_layers, use_cuda=False)
        grayscale_cam = cam(input_tensor=input_img, targets=None)
        grayscale_cam = grayscale_cam[0, :]
        img = input_img.squeeze(0)
        rgb_img = np.transpose(img, (1, 2, 0))
        rgb_img = rgb_img.numpy()
        visualization = show_cam_on_image(org_img/255, grayscale_cam, use_rgb=True, image_weight=transparency)
        visualizations_list.append(visualization)

    return confidences_list, visualizations_list

title = "CIFAR10 trained on ResNet18 Model with GradCAM"
description = "A simple Gradio interface to infer on ResNet model, and get GradCAM results"
examples = [["cat.png", 0.5, -1],["dog.png", 0.5, -1]]

demo = gr.Interface(
    inference, 
    inputs=[
        gr.inputs.File(file_count="multiple"),
        gr.Slider(0, 1, value=0.5, label="Opacity of GradCAM"),
        gr.Slider(-2, -1, value=-2, step=1, label="Which Layer?")
    ], 
outputs = [gr.Label(num_top_classes=3), gr.Image(shape=(32, 32), label="Output", style={"width": "128px", "height": "128px"})],
    title=title,
    description=description,
    examples=examples,
)

demo.launch()