-
I have a question. The training loss of the HED network is relatively large, thousands or even higher, but the result is not bad. Why is the loss of the HED relatively large? Under normal circumstance…
-
## Issues
See linked tickets for details. The issues are closed to do not overflow the bug tracker. Tick a box once an failure is fixed.
* [ ] test_free_reference fails on ppc64le with python 3.…
-
_prepItem generates a domID, even if you pass in an id via the content array
``` js
$('#container').ScrollStory({
content: [{hed:'Headline1', id:'myid1'}, {hed, 'Headline2', id: 'myid2'}]
});
```…
-
The pre-trained model link is 404'ing:
http://vcl.ucsd.edu/hed/hed_pretrained_bsds.caffemodel
Additionally, the directory listing of http://vcl.ucsd.edu/ appears to be empty.
Can the repo own…
-
I have build a Hindi TTS using [https://github.com/pbaljeka/world_merlin]. But at last, I found out that .hed (question file) is missing required to synthesis new utterances.
How can Igenerate ".h…
-
Hello. I use gcc-4.8.5, CUDA 8.0 and cuDNN 6.0. I receive errors:
```
[ 2%] Built target proto
[ 2%] Building NVCC (Device) object src/caffe/CMakeFiles/cuda_compile.dir/util/cuda_compile_generate…
-
### Expected Behavior
> This model supports 7 control modes, including canny (0), tile (1), depth (2), blur (3), pose (4), gray (5), low quality (6).
https://huggingface.co/Shakker-Labs/FLUX.1-d…
-
Bit of a silly question:
When executing `formatBlock`, (e.g., `editor.composer.commands.exec("formatBlock", "blockquote");`), the resulting element retains any `class` value previously set on it. So,…
beep updated
12 years ago
-
The HED uses an old caffe, which is not compatible with the latest CUDNN v5 (2x faster reported by NVIDIA).
**If only for testing**, after some investigation, it seems that HED uses no specific layer…
-
Thank you so much for releasing the code!
I have a question concerning the training data used for BSDS500 dataset.
In the HED (Holistic edge detection) paper, they used only augmented data from th…