Spaces:
Sleeping
Sleeping
File size: 2,579 Bytes
d728dec |
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 |
import gradio as gr
import math
import os
import cv2
import numpy as np
import torch
import segmentation_models_pytorch as smp
def pad_to_divisible(img, div=32):
h, w, _ = img.shape
new_h = math.ceil(h / div) * div
new_w = math.ceil(w / div) * div
pad_bottom = new_h - h
pad_right = new_w - w
padded = cv2.copyMakeBorder(img, 0, pad_bottom, 0, pad_right, cv2.BORDER_CONSTANT, value=[0, 0, 0])
return padded
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print("Using device:", device)
model_path = "best_unet_model_complete.pth"
if os.path.exists(model_path):
loaded_model = torch.load(model_path, map_location=device)
loaded_model.eval()
print("Loaded complete model from", model_path)
else:
raise FileNotFoundError(f"Model file not found at {model_path}")
def predict(image):
"""
Takes an input image (as a NumPy array), pads it, performs inference,
and returns:
- the padded input image,
- the predicted mask (grayscale), and
- the original image with a red overlay on the predicted regions.
"""
if image.shape[2] == 4:
image = cv2.cvtColor(image, cv2.COLOR_RGBA2RGB)
external_image_rgb = image.copy()
external_image_padded = pad_to_divisible(external_image_rgb, div=32)
external_image_norm = external_image_padded.astype(np.float32) / 255.0
external_tensor = torch.from_numpy(external_image_norm).permute(2, 0, 1)
external_tensor = external_tensor.unsqueeze(0).to(device)
with torch.no_grad():
output = loaded_model(external_tensor)
pred_mask = (torch.sigmoid(output) > 0.3).float()
pred_mask_np = pred_mask.cpu().squeeze().numpy()
overlay_image = external_image_padded.astype(np.float32)
mask_bool = pred_mask_np > 0.5
red_color = np.array([255, 0, 0], dtype=np.float32)
alpha = 0.5
overlay_image[mask_bool] = (1 - alpha) * overlay_image[mask_bool] + alpha * red_color
overlay_image = np.clip(overlay_image, 0, 255).astype(np.uint8)
return external_image_padded, pred_mask_np, overlay_image
demo = gr.Interface(
fn=predict,
inputs=gr.Image(type="numpy", label="Upload Image"),
outputs=[
gr.Image(label="Padded Image"),
gr.Image(label="Predicted Mask"),
gr.Image(label="Overlay (Predicted Regions)")
],
title="Wrinkle Segmentation",
description="Upload an image to see wrinkle segmentation. The app displays the padded image, the predicted mask, and an overlay of the predicted regions in red."
)
demo.launch() |