|
|
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 |
|
|
import custom_resnet |
|
|
from utils import nn |
|
|
import gradio as gr |
|
|
|
|
|
loss_criterion = nn.CrossEntropyLoss() |
|
|
lr = 0.1 |
|
|
model = custom_resnet.getModel(loss_criterion, lr) |
|
|
model.load_state_dict(torch.load("saved_model.pth", map_location=torch.device('cpu')), strict=False) |
|
|
|
|
|
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,num_classes=3,show_gradcam="yes", 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) |
|
|
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)} |
|
|
sorted_confidences = {k: v for k, v in sorted(confidences.items(), key=lambda item: item[1], reverse=True)} |
|
|
sorted_confidences = dict(list(sorted_confidences.items())[:num_classes]) |
|
|
_, prediction = torch.max(outputs, 1) |
|
|
target_layers = [model.convblockL3R1[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 = None |
|
|
if (show_gradcam == "yes") : |
|
|
visualization = show_cam_on_image(org_img/255, grayscale_cam, use_rgb=True, image_weight=transparency) |
|
|
else : |
|
|
visualization = show_cam_on_image(org_img/255, grayscale_cam, use_rgb=True, image_weight=1) |
|
|
return sorted_confidences, visualization, |
|
|
|
|
|
title = "TSAI S12 Assignment: CIFAR10 trained on Custom Model with GradCAM" |
|
|
description = "A simple Gradio interface to infer on Custom ResNet model, and get GradCAM results. Please use images that belong to any of these classes - 'plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck'." |
|
|
examples = [["cat.jpg",3,"yes", 0.5, -1], |
|
|
["Elsa.jpg", 3,"yes",0.5, -1], |
|
|
["horse.jpg", 3,"yes",0.5, -1], |
|
|
["Frog.png", 3,"yes",0.5, -1], |
|
|
["Bird.png", 3,"yes",0.5, -1], |
|
|
["deer.png", 3,"yes",0.5, -1], |
|
|
["Plane.png", 3,"yes",0.5, -1], |
|
|
["Ship.png", 3,"yes",0.5, -1], |
|
|
["car.png", 3,"yes",0.5, -1], |
|
|
["truck.png", 3,"yes",0.5, -1] |
|
|
] |
|
|
demo = gr.Interface( |
|
|
inference, |
|
|
inputs = [gr.Image(shape=(32, 32), label="Input Image"), gr.Slider(2, 10, value = 3,step = 1, label="Number of top classes"), gr.Radio(["yes", "no"], label="Show Gradcam"),gr.Slider(0, 1, value = 0.5, label="If yes, Opacity of GradCAM"), gr.Slider(-2, -1, value = -2, step=1, label="If yes, Which Layer?")], |
|
|
outputs = [gr.Label(num_top_classes=10), gr.Image(shape=(32, 32), label="Output").style(width=128, height=128)], |
|
|
title = title, |
|
|
description = description, |
|
|
examples = examples, |
|
|
) |
|
|
demo.launch() |
