MCPcopy Create free account
hub / github.com/DragonisCV/RAM / process_image

Function process_image

inference/inference.py:37–54  ·  view source on GitHub ↗
(img_path, model, device, args)

Source from the content-addressed store, hash-verified

35 return model
36
37def process_image(img_path, model, device, args):
38 imgname = osp.splitext(osp.basename(img_path))[0]
39 print('processing image: ', imgname)
40 img = cv2.imread(img_path, cv2.IMREAD_COLOR).astype(np.float32) / 255.
41 img = torch.from_numpy(np.transpose(img[:, :, [2, 1, 0]], (2, 0, 1))).float()
42 img = img.unsqueeze(0).to(device)
43 mean = np.array([0.485, 0.456, 0.406])
44 std = np.array([0.229, 0.224, 0.225])
45
46 normalize(img, mean, std, inplace=True)
47 with torch.no_grad():
48 output = model(img)
49 output = normalize(output, -1 * mean / std, 1 / std)
50 output = output.data.squeeze().float().cpu().clamp_(0, 1).numpy()
51 if output.ndim == 3:
52 output = np.transpose(output[[2, 1, 0], :, :], (1, 2, 0))
53 output = (output * 255.0).round().astype(np.uint8)
54 cv2.imwrite(osp.join(args.output, f'{imgname}_{args.model}.png'), output)
55
56def main():
57 parser = argparse.ArgumentParser()

Callers 1

mainFunction · 0.85

Calls

no outgoing calls

Tested by

no test coverage detected