KleinXin

Results 11 issues of KleinXin

I am using numpy 1.15.4 and pytorch 0.4.1. Error reported when I run the test codes with error message `File "upsnet/../upsnet/bbox/bbox_transform.py", line 15, in from .bbox import bbox_overlaps as bbox_overlaps_cython...

CUDA_VISIBLE_DEVICES=0,1,2,3 python3 -m torch.distributed.launch --nproc_per_node=4 train.py xxx The codes above cannot run on multiple GPUs. It is weird that all the trainning are running on the first GPU. Then if...

First of all, thank you for your greate work. I have a gender recognition project. The dataset I am using now is Celeba. I divide the dataset to female and...

In the line 35 of run.py, it seems GPUs are not used. ![image](https://user-images.githubusercontent.com/13084622/58558604-d7724f00-8253-11e9-9031-1336f92a4702.png) When I run the program in training mode, the memory of GPUs are not used. I guess...

It seems the codes only support single GPU trainning. Is it possible to train on multiple GPUs? thx

In line 512 of train/train.py, it says 'self.model.train_op' should be run. However, I could not find train_op in either basic_model and other model files. Anyone can help? Thx!

### System Info ```Shell accelerate 0.12.0 torch 1.12.0 torchvision 0.13.0 ``` ### Information - [X] The official example scripts - [ ] My own modified scripts ### Tasks - [X]...

bug

Is the link https://deepai.org/dataset/set14-super-resolution already out of dates?

In the tensorflow implementation, it has a function that the geometry of the scene can be extracted as cubes. https://github.com/bmild/nerf https://github.com/bmild/nerf/blob/master/extract_mesh.ipynb Is it also possible in this pytorch project?