DexiNed

DexiNed copied to clipboard

I do not know how to use the MDBD dataset, I don't know its file structure. Anyone can tell me ?

cainiaoqiuzhu

Could you publish NYUD preprocessing script?

4

I'm interested in how do you extract boundaries from NYUDv2

shkarupa-alex

Training with run_model.py: TypeError: expected str, bytes or os.PathLike object, not NoneType

3

I downloaded the checkpoint files from the google drive link and placed them in ./DexiNed-master/DexiNed-TF2/DXN_BIPED and then ran python run_model.py --image_width=512 --image_height=512 and got the error below Traceback (most recent...

za13

That gonna help lot of project using this work easily!

MrForExample

How to output the Output6 of edge-maps in DexiNed-TF2

3

I prefer the Output6 of edge-maps to the average or fused edge detection results o. What should I do in DexiNed-TF2 code? Looking forward to your reply

zongtianhu

Mean BGR values for PyTorch pretrained model?

3

What is the mean BGR values for the PyTorch pretrained model? [104.00699, 116.66877, 122.67892, 137.86], [103.939,116.779,123.68], or [104.00699, 116.66877, 122.67892] But they seemed to be quite similar.

xiankgx

[Extension Idea] A flask/fastapi server on top of DexiNed

1

Basic Idea: Exposing DexiNed as an API service. Users should be able to make API calls with relevant arguments to mimic CLI operations. I am willing to work on this....

Prakash2403

non-broadcastable output operand with shape () doesn't match the broadcast shape (3,)

1

I try to train my own dataset , I got an error : /home/lab606/anaconda3/envs/dexined/bin/python /home/lab606/code/DexiNed/DexiNed-Pytorch/main.py Number of GPU's available: 1 Pytorch version: 1.0.1.post2 mean_bgr: [104.00699, 116.66877, 122.67892] Mon Aug 31...

G-YY

Have you considered using CapsNets?

6

See: https://arxiv.org/abs/1710.09829v2 and https://www.oreilly.com/content/introducing-capsule-networks/ They are supposed to provide better results with fewer training examples. I'm going to translate your updated `TF2` version to a CapsNet and see if it...

stephenwithav

Curious: Why do _DenseLayer and _DenseBlock extend nn.Sequential instead of nn.Module?

23

Is there a benefit to extending `nn.Sequential` instead of, e.g.: ```python class _DenseBlock(nn.Module): def __init__(self, num_layers, input_features, out_features): super(_DenseBlock, self).__init__() for i in range(num_layers): layer = nn.Sequential(['conv/bn/relu/conv/bn']) # Swapped for...

stephenwithav