|
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 Assignment12Resnet |
|
import random |
|
import os |
|
pl_model = Assignment12Resnet.load_from_checkpoint("epoch=22-step=4140.ckpt",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') |
|
model = pl_model.model |
|
model_dict = dict(zip([-3,-2,-1],[pl_model.model.layer3.transition_block.transition_block,pl_model.model.layer3.conv_block1.conv_bn_block,pl_model.model.layer3.conv_block2.conv_bn_block])) |
|
|
|
def load_images_from_folder(num_misclassified,folder=None): |
|
print(type(num_misclassified)) |
|
images = [] |
|
for filename in os.listdir(folder): |
|
if filename.endswith(".jpg") or filename.endswith(".png"): |
|
img = Image.open(os.path.join(folder, filename)) |
|
images.append(img) |
|
return random.choices(images, k=int(num_misclassified)) |
|
def inference(input_img, show_gradcam = True ,num_gradcam_images=1, target_layer_number =-1,opacity= 0.5,show_misclassified = True,num_misclassified_images =10,num_top_classes=3): |
|
|
|
org_img = input_img |
|
input_img = pl_model.test_transform(input_img) |
|
input_img = input_img.unsqueeze(0) |
|
model.eval() |
|
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) |
|
if show_gradcam: |
|
target_layers = model_dict[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) |
|
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=opacity) |
|
else: |
|
visualization = org_img |
|
|
|
misclassified_images = None |
|
if show_misclassified: |
|
misclassified_images = load_images_from_folder(num_misclassified_images,folder = './misclassified_images') |
|
|
|
return confidences, visualization, misclassified_images |
|
|
|
title = "CIFAR10 trained on Custom ResNet Model with GradCAM" |
|
description = "A simple Gradio interface to infer on Custom ResNet model and get GradCAM results" |
|
examples = [["cat.jpg",True,1,-2, 0.5, True,5,3], ["dog.jpg",True,1,-2, 0.5, True,5,3 ],["bird.jpg",True,1,-2, 0.5, True,5,3],["ship.jpg",True,1,-2, 0.5, True,5,3],["truck.jpg",True,1,-2, 0.5, True,5,3],["deer.jpg",True,1,-2, 0.5, True,5,3],["frog.jpg",True,1,-2, 0.5, True,5,3],["horse.jpg",True,1,-2, 0.5, True,5,3],["plane.jpg",True,1,-2, 0.5, True,5,3]] |
|
|
|
demo = gr.Interface(inference,inputs=[ gr.Image(shape=(32, 32)), |
|
gr.Checkbox(value=True,label="Show GradCAM Images",show_label=True), |
|
gr.Number(value=1, label="Number of GradCAM Images", minimum=1, maximum=1), |
|
gr.Slider(minimum = -3,maximum=-1, value=-1, step=1, label="Which Layer?"), |
|
gr.Slider(minimum =0, maximum = 1.0, value=0.5, label="Opacity of GradCAM"), |
|
gr.Checkbox(label="Show Misclassified Images", value=True,show_label=True), |
|
gr.Number(value=5, label="Number of Misclassified Images (max 10)", minimum=1, maximum=10), |
|
gr.Number(value=3, label="Number of Top Classes (max 10)", minimum=1, maximum=10) |
|
], |
|
outputs=[ |
|
gr.Label(num_top_classes=3), |
|
gr.Image(shape=(32, 32), label="Output").style(width=128, height=128), |
|
gr.Gallery(label="Misclassified Images") |
|
], |
|
title=title, |
|
description=description, |
|
examples=examples, |
|
) |
|
|
|
|
|
demo.launch() |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
