hed

hed copied to clipboard

would be useful to use HED for binary edge detection task?

3

Thank you for sharing your implementation. I am wondering would be useful to use the HED network for the binary edge detection for the custom dataset? Here is an example...

NdaAzr

its about DeepFashion2

3

Sorry to write here about DeepFashion2 I was seeing your comments on DeepFashion2 you have trained model. Can you guide how to train DeepFashion2 I tried it but it was...

tomriddle54

Add a license

2

Thanks so much for your implementation! It's been really helpful for understanding HED. Could you add a license for the code? That would make it more clear what you allow...

wkevwang

How can i get the new statistics number in the 'datasets.py' file for new dataset

1

In the datasets.py file, the original code is like this: image = image - np.array((104.00698793, # Minus statistics. 116.66876762, 122.67891434)) but How can i get the new statistics number for...

tqwhdx19

Question about average_batch_loss

2

Thanks for your code and the model I trained is quite good(ODS=0.788.OIS=0.806)。 I just have a question when i see the log during the training,the epoch average batch_loss maintains at...

B1gBattery

Question

1

When we evaluate the result，we need to run the EdgeEvalDir.m，but what's the meaning of maxDist. I am confused about it and there isn't code.Can you explian it or give some...

CNHNLP

Question about outputting 5 side-outputs

1

Hello, thanks for sharing! I want to get the five side-outputs however Pytorch is different to caffe. Is there any suggestions? Thanks a lot! Looking forward to your reply!

Johnhave

question ablout hed_pretrained_bsds.py36pickle

2

Thanks for this progect! My compilation for Caffe or [modified HED](https://github.com/zeakey/hed) doesn't sussess. I noticed cafffemodel can be converted into pickle with some [tools](https://github.com/pierluigiferrari/caffe_weight_converter). But it still uses Caffe as...

bdseal

Weights initialization in the 1x1 conv

1

Hi @xwjabc Thanks for your contribution, I have a question just in the line below: ``` else: # Zero initialization following official repository. # Reference: hed/docs/tutorial/layers.md m.weight.data.zero_() ``` I see...

xavysp

issues about the learning rate

2

Thanks for sharing your code and it works well. I have some doubts about the learning rate. Why learning rate for conv5 is 100x of base learning rate, and classification...

tengteng95