PyTorch-Encoding

PyTorch-Encoding copied to clipboard

RuntimeError: CUDA out of memory. Tried to allocate 20.00 MiB (GPU 0; 3.82 GiB total capacity; 2.20 GiB already allocated; 27.88 MiB free; 2.32 GiB reserved in total by PyTorch)

1

How can I pass the batch_size to an script that is making use of encoding python package? ``` (torchenc) mona@goku:~$ python test_torch_encoding.py --batch_size 8 Traceback (most recent call last): File...

monacv

File "/home/mona/venv/torchenc/lib/python3.8/site-packages/torch/cuda/__init__.py", line 172, in _lazy_init torch._C._cuda_init() RuntimeError: CUDA unknown error - this may be due to an incorrectly set up environment, e.g. changing env variable CUDA_VISIBLE_DEVICES after program start. Setting the available devices to be zero. (torchenc) mona@goku:~$ echo $CUDA_VISIBLE_DEVICES

1

Could you please suggest how I should fix this problem? ``` (torchenc) mona@goku:~$ python test_torch_encoding.py /home/mona/venv/torchenc/lib/python3.8/site-packages/torch/cuda/__init__.py:52: UserWarning: CUDA initialization: CUDA unknown error - this may be due to an incorrectly...

monacv

I can not import

10

 just like this.it just stopped here.

lk1048453160

Error

1

Traceback (most recent call last): File "eval.py", line 185, in main() File "eval.py", line 86, in main model = neurvps.models.VanishingNet( File "C:\Users\Dimple\neurvps\neurvps\models\vanishing_net.py", line 23, in __init__ self.anet = ApolloniusNet(output_stride, upsample_scale)...

twister1606

RuntimeError in PyTorch 1.6

8

I am using pytorch 1.6.0, CUDA 10.2 and Pytorch_encoding master branch. ``` Traceback (most recent call last): File "train_SSL.py", line 612, in main() File "train_SSL.py", line 438, in main pred...

zhangbin0917

with specification below ``` torch==1.4.0 torchvision==0.5.0 pycocotools==2.0.0 ``` I run ``` python setup.py install in the working directory ``` and run ``` python train_dist.py --dataset coco --model deeplab --backbone resnest50...

danirisdiandita

请问一下训练集有分验证集出来吗？

5

想知道您划分的比例是多少，因为我按照您的代码运行出来的准确率有点差异。代码中每隔10个迭代次数进行一次测试还是验证？谢谢您的回答。

roseif

Hi, I'm working on converting the trained model to format .pt which can be used in c++, and there are some functions not supported by TorchScript(torch.jit). In functions/encoding.py line 61...

ciderpark

Mixed precision training

1

Are there plans to enable mixed precision training? Thanks

jgsimard

ImportError: libtorch_cpu.so

5

Hi, I found this error when I use torch 1.4  but when I upgrade to torch version to 1.5, I found this error  can anybody help me with...

tryanbot