DeepHyperX

DeepHyperX copied to clipboard

Would be nice to make HCube inferencw faster using parallel model deploy into 2+ GPUs. Any options ?

air55555

why during validation not using model.eval()?

1

Since some model have BN,dropout layers, why dont use model.eval() in the val function? am really confused, hope someone can help me. thx in advance.

Ponytai1j

because of I am interesting hsi classification using gan.

dlagez

Tensorboard

1

Migrate visualization from Visdom to Tensorboard

nshaud

Batch training

1

I'm trying to train a model with multiple images at once. It seems I need to change the DATASETS_CONFIG. If anyone has any insight into what the method is, your...

Jasonwtw

Why the lose value is Nan at the beginning of training sometimes？

1

**Describe the bug** A clear and concise description of what the bug is. **To Reproduce** Steps to reproduce the behavior (e.g. the command that you used). **Expected behavior** A clear...

Lzyin

how it run my own data？

1

can it run my own data with 3D-CNN? please teach me.

adminmyw

HI ~ Thanks for your great work, Recently I am trying to reproduce the experiment on paper. But I found there are no accurate experiment settings in the part of...

challow0

Have issue with the 'disjoint' eksperiment

1

Hi, I have tried to run your code with "hu" model and sampling_mode "disjoint". However, I got a worse result than the result in Table 3 of your paper. Is...

Weejaa04

Can't obtain Table III results with Li's 3D CNN network

1

Hi, I am testing Li's 3D CNN network on IndianPines dataset. In table III in disjoint mode, you have an accuracy of 75%. I can't reach more than 65%. -...

maudBqd