Hi Caro and Dmitry,

This sounds like a topaz, rather than a relion, problem. Can you use the 
same topaz installation as a stand-alone? Investigating that might lead 
to an answer.

HTH,

Sjors


On 02/03/2023 13:30, Caroline Haupt wrote:
> Dear @Takanori and all,
>
> I am still experiencing the issue with Topaz.
>
> Could you please give some advice how to solve this problem?
>
> The *.sav file was also not created although the Topaz picking process seems to finish.
> Please see below
>
> Thanks a lot.
>
> Best regards,
> Caro and Dmitry
>
>
>
>
> ==================================================
>
>   + Training with 130 picks in test set; and 512 picks in work set
>   + By setting aside 30 micrographs for the test set
> # Loading model: resnet8
> # Model parameters: units=32, dropout=0.0, bn=on
> # Loading pretrained model: resnet8_u32
> # Receptive field: 71
> UserWarning:
> NVIDIA GeForce RTX 3090 with CUDA capability sm_86 is not compatible with the current PyTorch installation.
> The current PyTorch install supports CUDA capabilities sm_37 sm_50 sm_60 sm_70.
> If you want to use the NVIDIA GeForce RTX 3090 GPU with PyTorch, please check the instructions at https://pytorch.org/get-started/locally/
>
> # Using device=0 with cuda=True
> # Loaded 91 training micrographs with 512 labeled particles
> # Loaded 30 test micrographs with 130 labeled particles
> # source        split   p_observed      num_positive_regions    total_regions
> # 0     train   0.000415        39581   95420416
> # 0     test    0.000317        9968    31457280
> # Specified expected number of particle per micrograph = 200.0
> # With radius = 5
> # Setting pi = 0.01544952392578125
> # minibatch_size=256, epoch_size=1000, num_epochs=10
> Traceback (most recent call last):
>    File "/usr/local/bin/topaz", line 8, in <module>
>      sys.exit(main())
>    File "/usr/local/lib/python3.6/site-packages/topaz/main.py", line 148, in main
>      args.func(args)
>    File "/usr/local/lib/python3.6/site-packages/topaz/commands/train.py", line 695, in main
>      , save_prefix=save_prefix, use_cuda=use_cuda, output=output)
>    File "/usr/local/lib/python3.6/site-packages/topaz/commands/train.py", line 577, in fit_epochs
>      , use_cuda=use_cuda, output=output)
>    File "/usr/local/lib/python3.6/site-packages/topaz/commands/train.py", line 557, in fit_epoch
>      metrics = step_method.step(X, Y)
>    File "/usr/local/lib/python3.6/site-packages/topaz/methods.py", line 103, in step
>      score = self.model(X).view(-1)
>    File "/usr/local/lib64/python3.6/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
>      return forward_call(*input, **kwargs)
>    File "/usr/local/lib/python3.6/site-packages/topaz/model/classifier.py", line 28, in forward
>      z = self.features(x)
>    File "/usr/local/lib64/python3.6/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
>      return forward_call(*input, **kwargs)
>    File "/usr/local/lib/python3.6/site-packages/topaz/model/features/resnet.py", line 54, in forward
>      z = self.features(x)
>    File "/usr/local/lib64/python3.6/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
>      return forward_call(*input, **kwargs)
>    File "/usr/local/lib64/python3.6/site-packages/torch/nn/modules/container.py", line 141, in forward
>      input = module(input)
>    File "/usr/local/lib64/python3.6/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
>      return forward_call(*input, **kwargs)
>    File "/usr/local/lib/python3.6/site-packages/topaz/model/features/resnet.py", line 270, in forward
>      y = self.conv(x)
>    File "/usr/local/lib64/python3.6/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
>      return forward_call(*input, **kwargs)
>    File "/usr/local/lib64/python3.6/site-packages/torch/nn/modules/conv.py", line 446, in forward
>      return self._conv_forward(input, self.weight, self.bias)
>    File "/usr/local/lib64/python3.6/site-packages/torch/nn/modules/conv.py", line 443, in _conv_forward
>      self.padding, self.dilation, self.groups)
> RuntimeError: CUDA error: no kernel image is available for execution on the device
> CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect.
> For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
>   Done with training! Launch another Auto-picking job to use the model for picking coordinates.
>
> ########################################################################
>
> To unsubscribe from the CCPEM list, click the following link:
> https://www.jiscmail.ac.uk/cgi-bin/WA-JISC.exe?SUBED1=CCPEM&A=1
>
> This message was issued to members of www.jiscmail.ac.uk/CCPEM, a mailing list hosted by www.jiscmail.ac.uk, terms & conditions are available at https://www.jiscmail.ac.uk/policyandsecurity/
>
-- 
Sjors Scheres
MRC Laboratory of Molecular Biology
Francis Crick Avenue, Cambridge Biomedical Campus
Cambridge CB2 0QH, U.K.
tel: +44 (0)1223 267061
http://www2.mrc-lmb.cam.ac.uk/groups/scheres

########################################################################

To unsubscribe from the CCPEM list, click the following link:
https://www.jiscmail.ac.uk/cgi-bin/WA-JISC.exe?SUBED1=CCPEM&A=1

This message was issued to members of www.jiscmail.ac.uk/CCPEM, a mailing list hosted by www.jiscmail.ac.uk, terms & conditions are available at https://www.jiscmail.ac.uk/policyandsecurity/