app.py

import torch, torchvision
from torchvision import transforms
import numpy as np
import gradio as gr
from PIL import Image
import os
import lightning as L
import torchmetrics
from pytorch_grad_cam import GradCAM
from pytorch_grad_cam.utils.image import show_cam_on_image
from model import LightningModel

pytorch_model = torch.hub.load('pytorch/vision', 'resnet18', weights=None)
pytorch_model.fc = torch.nn.Linear(512, 10)
model_pth = './epoch=22-step=16169.ckpt'
lightning_model = LightningModel.load_from_checkpoint(checkpoint_path=model_pth, model=pytorch_model, map_location=torch.device("cpu"))

inv_normalize = transforms.Normalize(
    mean=[-0.50/0.23, -0.50/0.23, -0.50/0.23],
    std=[1/0.23, 1/0.23, 1/0.23]
)
classes = ('plane', 'car', 'bird', 'cat', 'deer',
           'dog', 'frog', 'horse', 'ship', 'truck')

def inference(input_img, transparency = 0.5, target_layer_number = -1):
    transform = transforms.ToTensor()
    org_img = input_img
    input_img = transform(input_img)
    input_img = input_img
    input_img = input_img.unsqueeze(0)
    lightning_model.eval()
    with torch.no_grad():
        outputs = lightning_model(input_img)
        print(f'outputs, {outputs.shape}')
    softmax = torch.nn.Softmax(dim=0)
    print()
    o = softmax(outputs.flatten())
    confidences = {classes[i]: float(o[i]) for i in range(10)}
    _, prediction = torch.max(outputs, 1)
    target_layers = [pytorch_model.layer2[target_layer_number]]
    cam = GradCAM(model=lightning_model, target_layers=target_layers)
    grayscale_cam = cam(input_tensor=input_img, targets=None)
    grayscale_cam = grayscale_cam[0, :]
    img = input_img.squeeze(0)
    img = inv_normalize(img)
    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)
    print(confidences)
    return confidences, visualization

title = "CIFAR10 trained on ResNet18 Model with GradCAM"
description = "A simple Gradio interface to infer on ResNet model, and get GradCAM results"
example1 = './cat.jpg'
example2 = './dog.jpg'
examples = [[example1, 0.5, -1], [example2, 0.5, -1]]
gradio_app = gr.Interface(
    inference,
    inputs = [gr.Image(width=32, height=32, label="Input Image"), 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(width=32, height=32, label="Output")],
    title = title,
    description = description,
    examples = examples,
)
gradio_app.launch()