Closed gevro closed 1 year ago
@gevro thank you for reporting. Can you share the command you are running?
singularity run -W /data -B /scratch/projects/bin/deepconsensus/model:/model -B `pwd` /scratch/projects/bin/deepconsensus/deepconsensus_1.0.0.sif deepconsensus run --batch_size=1024 --batch_zmws=100 --cpus 4 --max_passes 20 --subreads_to_ccs=subreads_to_ccs.bam --ccs_bam=ccs.bam --checkpoint=/model/checkpoint --output=output.deepconsensus.fastq
@gevro please try running singularity with a clean environment. I think passing --cleanenv
should work.
singularity run \
-W /data \
-B /scratch/projects/bin/deepconsensus/model:/model \
-B `pwd` \
--cleanenv \
/scratch/projects/bin/deepconsensus/deepconsensus_1.0.0.sif \
deepconsensus run \
--batch_size=1024 \
--batch_zmws=100 \
--cpus 4 \
--max_passes 20 \
--subreads_to_ccs=subreads_to_ccs.bam \
--ccs_bam=ccs.bam \
--checkpoint=/model/checkpoint \
--output=output.deepconsensus.fastq
For whatever reason, it appears you are using a shared version of the python library from your machine/HPC:
/share/apps/python/3.8.6/intel/lib/python3.8/site-packages/pandas/__init__.py
And this appears to be breaking things.
Now I'm getting this error:
2022-10-11 17:08:33.096036: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 AVX512F AVX512_VNNI FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
FATAL Flags parsing error: Unknown command line flag 'max_passes'
Pass --helpshort or --helpfull to see help on flags.
We removed the --max_passes
flag in this release because we have not provided any models with alternative numbers of passes. Please try removing this flag:
singularity run \
-W /data \
-B /scratch/projects/bin/deepconsensus/model:/model \
-B `pwd` \
--cleanenv \
/scratch/projects/bin/deepconsensus/deepconsensus_1.0.0.sif \
deepconsensus run \
--batch_size=1024 \
--batch_zmws=100 \
--cpus 4 \
--subreads_to_ccs=subreads_to_ccs.bam \
--ccs_bam=ccs.bam \
--checkpoint=/model/checkpoint \
--output=output.deepconsensus.fastq
Also - the --max_passes
, and --example_width
flags are now dictated by the model params.json - so there is no need to set these flags.
Ok working now. Thanks.
Hi, Getting this error with new deepconsensus 1.0.0. I'm running the exact same command that worked for the previous deepconsensus version. I'm running from the docker.