|
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 |
|
|
|
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, transparency = 0.5, target_layer_number = -1, num_top_classes = 5): |
|
"""This function take input as an image and generate Grad Cam image of it. |
|
|
|
Args: |
|
input_img (_type_): Input image provided by user. |
|
transparency (float, optional): _description_. Defaults to 0.5. |
|
target_layer_number (int, optional): Output of layer which will be given to Grad Cam. Defaults to -1. |
|
num_top_classes (int, optional): To show number of classes to show in the output. Defaults to 5. |
|
|
|
Returns: |
|
top: Top Classes and Confidence level of the prediction |
|
visualization: Grad Cam output |
|
""" |
|
|
|
transform = transforms.Compose([ |
|
transforms.ToTensor(), |
|
transforms.Normalize((0.1307,), (0.3081,)) |
|
]) |
|
org_img = input_img |
|
input_img = transform(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)} |
|
|
|
_, prediction = torch.max(outputs, 1) |
|
target_layers = [model.layer3_r3[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) |
|
|
|
|
|
sorted_confidences = {k: v for k, v in sorted(confidences.items(), key=lambda item: item[1], reverse=True)} |
|
top_classes = list(sorted_confidences.keys())[:num_top_classes] |
|
top = dict((k,v) for k, v in sorted_confidences.items() if k in top_classes) |
|
|
|
return top, visualization |
|
|
|
title = "CIFAR10 trained on ResNet18 Model with GradCAM" |
|
description = "A simple Gradio interface to infer on ResNet model, and get GradCAM results" |
|
examples = [["airplane.png", 0.5, -1, 5],["bird.jpeg", 0.5, -1, 5], ["car.jpeg", 0.5, -1, 5], ["cat.png", 0.5, -1, 5], |
|
["deer.jpeg", 0.5, -1, 6], ["dog.png", 0.5, -1, 7], ["frog.jpeg", 0.5, -1, 4], ["horse.png", 0.5, -1, 7], |
|
["ship.png", 0.5, -1, 3], ["truck.jpeg", 0.5, -1, 8]] |
|
|
|
demo = gr.Interface( |
|
inference, |
|
inputs = [gr.Image(shape=(32, 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?"), |
|
gr.Slider(0, 10, value = 1, step=1, label="Number of Top Classes")], |
|
outputs = [gr.Label(num_top_classes=10), gr.Image(shape=(32, 32), label="Output", style={"width": "128px", "height": "128px"})], |
|
title = title, |
|
description = description, |
|
examples = examples, |
|
) |
|
|
|
demo.launch() |
|
|
