how to see all test image results after run the inference.py? about pytorch-pyramid-feature-attention-network-for-saliency-detection HOT 2 CLOSED

thanks! I have got it. However, I meet another question, the ouput images Rounded-off Saliency Mask looks much better than Generated Saliency Mask , which is the real result of this method?
` for batch_idx, (img_np, img_tor) in enumerate(inf_dataloader, start=1):
img_tor = img_tor.to(device)
pred_masks, _ = model(img_tor)

        # Assuming batch_size = 1
        img_np = np.squeeze(img_np.numpy(), axis=0)
        img_np = img_np.astype(np.uint8)
        img_np = cv2.cvtColor(img_np, cv2.COLOR_RGB2BGR)
        pred_masks_raw = np.squeeze(pred_masks.cpu().numpy(), axis=(0, 1))
        pred_masks_round = np.squeeze(pred_masks.round().cpu().numpy(), axis=(0, 1)

        print('Image :', batch_idx)
        cv2.imshow('Input Image', img_np)
        cv2.imshow('Generated Saliency Mask', pred_masks_raw)
        cv2.imshow('Rounded-off Saliency Mask', pred_masks_round)`

from pytorch-pyramid-feature-attention-network-for-saliency-detection.

In the raw saliency mask pixel values are between 0 and 1 (this is the output directly from the model), while in the rounded off saliency mask the pixel values are either 0 or 1. The later one looks better as some of the surrounding noise is removed and the resultant mask is much sharper.

from pytorch-pyramid-feature-attention-network-for-saliency-detection.