Yuge Zhang
Yuge Zhang
I'll give you some clue: * You mentioned you are using 1 GPU, why is this in your log: `Using GPUs: [0, 1, 2, 3, 4, 5, 6, 7]` *...
> PR to master / PR to cuda-11(new branch) which do you prefer? Please PR to master branch. > Is there any other contribution guideline? If it's not a huge...
For example, you need to map [0, 800] to [-1, 1]. You need to do this: 1. minus 800 2. divide by 400 (which is 800/2).
I think you can read the `predict` first. It might give you a sense about what's going on in the model.
Maybe you should ask google about this, or please provide more details about why google can't help.
Sorry I think this repo is bit of out of maintanence. If you are not interested in digging out the reason, you can try with pytorch version mentioned in readme.
You mean [this](https://github.com/noahcao/Pixel2Mesh/blob/master/experiments/default/resnet.yml)?
Need to be tested on K8S pipline. Tracked in #4954.
/azp run full test - compression
/azp run full test - compression