adding main, model.pth and input files

README.md

@@ -1,8 +1,8 @@
 ---
-title: Image Classification
-emoji: 🐠
-colorFrom: pink
-colorTo: indigo
+title: Demo1
+emoji: 🚀
+colorFrom: gray
+colorTo: gray
 sdk: gradio
 sdk_version: 3.39.0
 app_file: app.py

app.py

@@ -0,0 +1,54 @@
+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 resnet import ResNet18
+import gradio as gr
+
+model = ResNet18()
+model.load_state_dict(torch.load("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, 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)}
+    _, prediction = torch.max(outputs, 1)
+    target_layers = [model.layer2[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=transparency)
+    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"
+examples = [["cat.jpg", 0.5, -1], ["dog.jpg", 0.5, -1]]
+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?")], 
+    outputs = [gr.Label(num_top_classes=3), gr.Image(shape=(32, 32), label="Output").style(width=128, height=128)],
+    title = title,
+    description = description,
+    examples = examples,
+)
+demo.launch()

model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cf9335b863d513421b678d5b93078c44eca26d4d1a7afdd7411cc27d4b907b9
+size 133

requirements.txt

@@ -0,0 +1,6 @@
+torch
+torchvision
+torch-lr-finder
+grad-cam
+pillow
+numpy

resnet.py

@@ -0,0 +1,76 @@
+"""
+ResNet in PyTorch.
+For Pre-activation ResNet, see 'preact_resnet.py'.
+
+Reference:
+[1] Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun
+    Deep Residual Learning for Image Recognition. arXiv:1512.03385
+"""
+import torch.nn as nn
+import torch.nn.functional as F
+
+
+class BasicBlock(nn.Module):
+    expansion = 1
+
+    def __init__(self, in_planes, planes, stride=1):
+        super(BasicBlock, self).__init__()
+        self.conv1 = nn.Conv2d(in_planes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
+        self.bn1 = nn.BatchNorm2d(planes)
+        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=1, padding=1, bias=False)
+        self.bn2 = nn.BatchNorm2d(planes)
+
+        self.shortcut = nn.Sequential()
+        if stride != 1 or in_planes != self.expansion*planes:
+            self.shortcut = nn.Sequential(
+                nn.Conv2d(in_planes, self.expansion*planes, kernel_size=1, stride=stride, bias=False),
+                nn.BatchNorm2d(self.expansion*planes)
+            )
+
+    def forward(self, x):
+        out = F.relu(self.bn1(self.conv1(x)))
+        out = self.bn2(self.conv2(out))
+        out += self.shortcut(x)
+        out = F.relu(out)
+        return out
+
+
+class ResNet(nn.Module):
+    def __init__(self, block, num_blocks, num_classes=10):
+        super(ResNet, self).__init__()
+        self.in_planes = 64
+
+        self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1, bias=False)
+        self.bn1 = nn.BatchNorm2d(64)
+        self.layer1 = self._make_layer(block, 64, num_blocks[0], stride=1)
+        self.layer2 = self._make_layer(block, 128, num_blocks[1], stride=2)
+        self.layer3 = self._make_layer(block, 256, num_blocks[2], stride=2)
+        self.layer4 = self._make_layer(block, 512, num_blocks[3], stride=2)
+        self.linear = nn.Linear(512*block.expansion, num_classes)
+
+    def _make_layer(self, block, planes, num_blocks, stride):
+        strides = [stride] + [1]*(num_blocks-1)
+        layers = []
+        for stride in strides:
+            layers.append(block(self.in_planes, planes, stride))
+            self.in_planes = planes * block.expansion
+        return nn.Sequential(*layers)
+
+    def forward(self, x):
+        out = F.relu(self.bn1(self.conv1(x)))
+        out = self.layer1(out)
+        out = self.layer2(out)
+        out = self.layer3(out)
+        out = self.layer4(out)
+        out = F.avg_pool2d(out, 4)
+        out = out.view(out.size(0), -1)
+        out = self.linear(out)
+        return out
+
+
+def ResNet18():
+    return ResNet(BasicBlock, [2, 2, 2, 2])
+
+
+def ResNet34():
+    return ResNet(BasicBlock, [3, 4, 6, 3])