File size: 3,680 Bytes
7e93243 1b661c7 7e93243 432628d cd6e155 67cda28 ca7dac7 67cda28 ca7dac7 998c6fe 72dc25c 998c6fe 5cd7415 998c6fe 76c88e2 76496e4 76c88e2 76496e4 7e93243 432628d 7e93243 7cf0aea 432628d 76c88e2 998c6fe 7e93243 150b753 ee170be |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 |
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.ToTensor()
transform = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))
])
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())
# exp_outputs = torch.exp(outputs.flatten())
confidences = {classes[i]: float(o[i]) for i in range(10)}
# confidences = {classes[i]: float(exp_outputs[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)
# Sort confidences dictionary in descending order of values and take top num_top_classes
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()
|