Update app.py

app.py

@@ -2,24 +2,19 @@ import torch
 import torch.nn as nn
 import pytorch_lightning as pl
 from torchvision.datasets import MNIST
-from torchvision.transforms import ToTensor
-from torch.utils.data import DataLoader, random_split
+from torch.utils.data import DataLoader, random_split, Dataset
 import torch
 import albumentations as A
 from albumentations.pytorch import ToTensorV2
-
 from torchvision import transforms
 import numpy as np
 import torch
 from torchvision import datasets
-from torch.utils.data import Dataset, DataLoader
 from torchvision.transforms import ToTensor
 from torchmetrics import Accuracy
 from torch.nn import functional as F
 import matplotlib.pyplot as plt
-
 import gradio as gr
-import torch
 from PIL import Image
 from Dataset.testalbumentation import TestAlbumentation
 from Model.Lit_cifar_module import LitCifar
@@ -34,16 +29,16 @@ classes = ('plane', 'car', 'bird', 'cat',
 global_classes = 5
 
 def inference(input_image, transparency, target_layer, num_top_classes1, gradcam_image_display = False):
- im = input_image
+ image = input_image
  test_transform = TestAlbumentation()
- im1 = test_transform(im)
- im1 = im1.unsqueeze(0).cpu()
- out0 = model(im1)
+ image1 = test_transform(image)
+ image1 = image1.unsqueeze(0).cpu()
+ out0 = model(image1)
  out = out0.detach().numpy()
  confidences = {classes[i] : float(out[0][i]) for i in range(10)}
  val = torch.argmax(out0).detach().numpy().tolist()
- targ = [val]
- input_image_np,visualization=gradcame(net, 0, targ, im1, target_layer, transparency)
+ target = [val]
+ input_image_np,visualization=gradcame(model, 0, target, image1, target_layer, transparency)
  return confidences, visualization
  
 interface = gr.Interface(inference,