Rui Zhang

Hi, I found deepEMhancer cannot launch on my workstation with 8x GeForce RTX 3090 GPUs and CUDA 11.1. It hangs at 0% progress after loading the model (see below), and...

Testing with 1 GPU showed very similar behavior: hangs at the first steps. I just noticed the GPU0 memory is actually fully loaded, maybe this is the problem? Is there...

Hmm, with -g -1, it seems to be stuck at 0% as well (I should say it progresses extremely slow, from 0/1600 to 1/1600). "top" command shows deepemhancer is using...

Hi, when specifying -g 0, top command shows 1 CPU is running, which seems to be normal. And "nvidia-smi" indicates some deepEM job is assigned to GPU.

Hi, I am getting this error message: (deepEMhancer_env2) zhangrui@sp:/data/deepEM_dir/test/$ ./z_deepEM.sh updating environment to select gpu: [0, 1, 2, 3, 4, 5, 6, 7] loading model /home/zhangrui/.local/share/deepEMhancerModels/production_checkpoints/deepEMhancer_highRes.hd5 ... Traceback (most recent...

Now it seems to be working fine! I will compare the results and let you know!

Unfortunately, the result seems to be completely wrong... (although it only took ~20 mins to finish a 512 box with 8x 3090 cards, it will take ~35 mins for 8x...

Now the result seems to be fine! And with -b 32 it only takes ~17 mins for a 512 box. Thank you so much for developing such a wonderful tool!...

Hi, My OS is Ubuntu 20.04.5 LTS When using only one gpu, the symptom is exactly the same (not progressing, GPU load ~100%) Here is the result of pip freeze...

Sorry for the delay ~(just came back from a conference) I waited for 15 mins but the progression bar didn't move at all. Same thing if I use a single...