As seen in #22, using torchvision's transformations produces better edges as compared to the original solution.

Unfortunately I am not able to test the ODS score with the repo you linked, but just from my untrained eyeballs it appears to be better. Will post more metrics later.

`Hello,

I took images from the BSDS dataset, and individually analyzed the F-Scores. I observed that the result is pretty bad in general, and I am not sure what I'm doing wrong. I am suspecting a bug, but I'm not confident.

Image vs ground truth:

HED output:

And of course, if the value of an individual cell is greater than 0.5, I round it off to 1 before estimating the F1 score. The image after rounding off looks like this:

Then, I calculate the F-Score using the following code:

Here, the gt is the groundtruth and the pred array is the prediction image from HED.

tp = np.sum(pred[np.where(pred == 1)] == gt[np.where(pred == 1)])
fp = np.sum(pred[np.where(pred == 1)] != gt[np.where(pred == 1)])
precision = tp / (tp + fp)

# recall
fn = np.sum(pred[np.where(pred == 0)] != gt[np.where(pred == 0)])
recall = tp / (tp + fn)

# f-value
fvalue = 2 * precision * recall / (precision + recall)

I get a value (F1 score) of 0.1 to 0.2. The paper and the Github descriptions state much higher values (>0.7). Can anyone guide me regarding what could be going wrong? Since I am using the same metric and the same score, it is a little tricky.

Any help is appreciated.

can you tell me how to open network-bsds500.pytorch（i.e.the file download use download.bash）, i use .txt or .py the file will change to garbled。so，can you provide .pth file,or tell me how to open it?

Traceback (most recent call last): File "run.py", line 153, in <module> tenOutput = estimate(tenInput) File "run.py", line 145, in estimate return netNetwork(tenInput.cuda().view(1, 3, intHeight, intWidth))[0, :, :, :].cpu() RuntimeError: shape '[1, 3, 320, 480]' is invalid for input of size 614400 I tried to test my own image, but I got this error. The difference between sample.png and my own image.png is the bit depth. Mine is 32 bit depth.

Hi, I noticed that in the forward function it normalizes the input as

tenBlue = (tenInput[:, 0:1, :, :] * 255.0) - 104.00698793
tenGreen = (tenInput[:, 1:2, :, :] * 255.0) - 116.66876762 
tenRed = (tenInput[:, 2:3, :, :] * 255.0) - 122.67891434

But when I noramlized it by ImageNet RGB mean[0.485, 0.456, 0.406] as follows:

tenBlue = tenInput[:, 0:1, :, :]  - 0.406
tenGreen = tenInput[:, 1:2, :, :] - 0.456
tenRed = tenInput[:, 2:3, :, :] - 0.485

The output become blurry: I feel very confused about this cause it seems to be same normalization process

Hi sniklaus, Thanks very much for u excellent implementation. There is a qusetion that I'd like to ask you for advice. Have you ever used HED's feature map as a supervised term, just similar to VGG loss? It would be greatly appreciated if you could offer me any suggestions! Best, Melon

HI ,good morning. So sorry to bother you . There are something wrong with the pretrained network as follows .

deserialized_objects[key]._set_from_file(f, offset, f_should_read_directly) RuntimeError: unexpected EOF, expected 4922858 more bytes. The file might be corrupted.

Hey,

I just wanted to run your re-implementation of the pytorch HED model and the weights url http://content.sniklaus.com/github/pytorch-hed/network-bsds500 seems to point nowhere.

Keep up the good work!

Hello, @sniklaus Thanks for your contribution! Is there a way to generate edges from multiple images under a specific directory with your run.py? It seemed that your run.py can only process a single image as input so far. Thanks.

Hi there, it seemed that your latest commit(https://github.com/sniklaus/pytorch-hed/commit/5ef88c378053e0c865f4a60eb69db4c7f2714e8e) didn't work well with PyTorch 1.6? After python run.py, I got the following error,

Traceback (most recent call last): File "run.py", line 154, in PIL.Image.fromarray((tenOutput.clip(0.0, 1.0).numpy().transpose(1, 2, 0)[:, :, 0] * 255.0).astype(numpy.uint8)).save(arguments_strOut) AttributeError: 'Tensor' object has no attribute 'clip'

When I changed the clip back to clamp, it worked. Could you be so kind to provide me with any clues on this? Thanks.

Traceback (most recent call last): File "run.py", line 152, in tenOutput = estimate(tenInput) File "run.py", line 135, in estimate netNetwork = Network().eval() File "run.py", line 95, in init self.load_state_dict({ strKey.replace('module', 'net'): tenWeight for strKey, tenWeight in torch.hub.load_state_dict_from_url(url='http://content.sniklaus.com/github/pytorch-hed/network-' + arguments_strModel + '.pytorch', file_name='hed-' + arguments_strModel).items() }) TypeError: load_state_dict_from_url() got an unexpected keyword argument 'file_name'