App code
Browse files
app.py
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import torch
|
| 2 |
+
import torch.nn as nn
|
| 3 |
+
from torchvision import transforms
|
| 4 |
+
from PIL import Image
|
| 5 |
+
import numpy as np
|
| 6 |
+
import gradio as gr
|
| 7 |
+
|
| 8 |
+
# -------- Define your U-Net model (same as training) --------
|
| 9 |
+
class UNet(nn.Module):
|
| 10 |
+
def __init__(self):
|
| 11 |
+
super(UNet, self).__init__()
|
| 12 |
+
# define your encoder-decoder here
|
| 13 |
+
# simplified example
|
| 14 |
+
self.conv1 = nn.Conv2d(1, 16, 3, padding=1)
|
| 15 |
+
self.conv2 = nn.Conv2d(16, 3, 3, padding=1)
|
| 16 |
+
|
| 17 |
+
def forward(self, x):
|
| 18 |
+
x = torch.relu(self.conv1(x))
|
| 19 |
+
x = torch.sigmoid(self.conv2(x))
|
| 20 |
+
return x
|
| 21 |
+
|
| 22 |
+
# -------- Load model --------
|
| 23 |
+
model = UNet()
|
| 24 |
+
model.load_state_dict(torch.load("unet_model.pth", map_location="cpu"))
|
| 25 |
+
model.eval()
|
| 26 |
+
|
| 27 |
+
# -------- Preprocessing & Postprocessing --------
|
| 28 |
+
def predict(image):
|
| 29 |
+
# Resize and convert to tensor
|
| 30 |
+
transform = transforms.Compose([
|
| 31 |
+
transforms.Resize((256, 256)),
|
| 32 |
+
transforms.ToTensor()
|
| 33 |
+
])
|
| 34 |
+
img = transform(image).unsqueeze(0) # add batch dimension
|
| 35 |
+
|
| 36 |
+
with torch.no_grad():
|
| 37 |
+
output = model(img)
|
| 38 |
+
|
| 39 |
+
# Convert output tensor to image
|
| 40 |
+
output_img = output.squeeze(0).permute(1, 2, 0).numpy()
|
| 41 |
+
output_img = (output_img * 255).astype(np.uint8)
|
| 42 |
+
return Image.fromarray(output_img)
|
| 43 |
+
|
| 44 |
+
# -------- Gradio Interface --------
|
| 45 |
+
iface = gr.Interface(
|
| 46 |
+
fn=predict,
|
| 47 |
+
inputs=gr.Image(type="pil"),
|
| 48 |
+
outputs=gr.Image(type="pil"),
|
| 49 |
+
title="U-Net Pseudo-Color Edge Detection",
|
| 50 |
+
description="Upload an image to see pseudo-color edge detection using U-Net."
|
| 51 |
+
)
|
| 52 |
+
|
| 53 |
+
iface.launch()
|