No such command 'train_model'

jlevy44 / PathFlowAI

A High-Throughput Workflow for Preprocessing, Deep Learning Analytics and Interpretation in Digital Pathology

https://jlevy44.github.io/PathFlowAI/

MIT License

38 stars 8 forks source link

No such command 'train_model' #25

Closed asmagen closed 4 years ago

asmagen commented 4 years ago

I encountered the following issue with running the training:

!pathflowai-train_model train_model -h
nonechucks may not work properly with this version of PyTorch (1.5.0). It has only been tested on PyTorch versions 1.0, 1.1, and 1.2
Usage: pathflowai-train_model [OPTIONS] COMMAND [ARGS]...
Try 'pathflowai-train_model -h' for help.

Error: No such command 'train_model'.

jlevy44 commented 4 years ago

Works fine for me. How did you install pathflow?

asmagen commented 4 years ago

Now I get

!pathflowai-train_model train_model -h
Error: mkl-service + Intel(R) MKL: MKL_THREADING_LAYER=INTEL is incompatible with libgomp.so.1 library.
    Try to import numpy first or set the threading layer accordingly. Set MKL_SERVICE_FORCE_INTEL to force it.

after the '512' output from the preprocessing discussed in #24

jlevy44 commented 4 years ago

I do not think this is an issue on our software’s end. Could be a missing dependency either via singularity or from your HPC. You could also try the recommendation that you had just sent me.