Closed akashparvatikar closed 3 years ago
Hi @AkashParvatikar, were there any errors in the notebook cell output for the cell containing "cytokit processor run_all"?
That is the step that would generate those files.
Hi, you are right. I am getting an error while trying to run the "processor" step cell.
error1: Invalid argument: 'visible_device_list' listed an invalid GPU id '1' but visible device count is 1. distributed.worker - WARNING - Compute Failed
error2: Exception: Exception('Failed to create session.',)
error3: E tensorflow/stream_executor/cuda/cuda_driver.cc:936] failed to allocate 4.00G (4294967296 bytes) from device: CUDA_ERROR_OUT_OF_MEMORY
Any thoughts on how to address this?
You'll have to modify the gpus
property in the experiment.yaml
file if you only have one GPU. That seems most likely given the error.
I am trying to run "marker_profiling_example" notebook and while trying to visualize the 6-channel image, I get the following error: No such file or directory: '/tmp/cytokit-example/cellular-marker/20181116-d40-r1-20x-5by5/output/v00/montage/best_z_segm/R001.tif'
I think montage folder is missing within v00. Can you please help me with this?