--phase_reads
--track_ref_reads
--output_phase_info
--output_local_read_phasing ./test-read-phasing_debug@2.tsv
seq 0 1 | parallel -q --halt 2 --line-buffer /opt/deepvariant/bin/make_examples \
--mode calling \
--ref "genome.fasta" \
--reads "test.paired_end.sorted.bam" \
--examples "./test.examples.tfrecord@2.gz" \
--gvcf "./test.gvcf.tfrecord@2.gz" \
--checkpoint "/opt/models/wgs" --call_small_model_examples --small_model_indel_gq_threshold "30" --small_model_snp_gq_threshold "25" --small_model_vaf_context_window_size "51" --trained_small_model_path "/opt/smallmodels/wgs/model.keras" \
--phase_reads --track_ref_reads --output_phase_info --output_local_read_phasing ./test-read-phasing_debug@2.tsv \
--task {}
> I0604 05:26:50.104848 140629058654656 make_examples_core.py:384] Task 1/2: Overhead for preparing inputs: 0 seconds
> Traceback (most recent call last):
> File "/tmp/Bazel.runfiles_ol4fhm23/runfiles/com_google_deepvariant/deepvariant/make_examples.py", line 239, in <module>
> app.run(main)
> File "/tmp/Bazel.runfiles_ol4fhm23/runfiles/absl_py/absl/app.py", line 312, in run
> _run_main(main, args)
> File "/tmp/Bazel.runfiles_ol4fhm23/runfiles/absl_py/absl/app.py", line 258, in _run_main
> sys.exit(main(argv))
> File "/tmp/Bazel.runfiles_ol4fhm23/runfiles/com_google_deepvariant/deepvariant/make_examples.py", line 229, in main
> make_examples_core.make_examples_runner(options)
> File "/tmp/Bazel.runfiles_ol4fhm23/runfiles/com_google_deepvariant/deepvariant/make_examples_core.py", line 3640, in make_examples_runner
> region_processor.call_small_model_examples_in_region(
> File "/tmp/Bazel.runfiles_ol4fhm23/runfiles/com_google_deepvariant/deepvariant/make_examples_core.py", line 2095, in call_small_model_examples_in_region
> sample.small_model_variant_caller.call_variants(
> File "/tmp/Bazel.runfiles_ol4fhm23/runfiles/com_google_deepvariant/deepvariant/small_model/inference.py", line 166, in call_variants
> genotype_probabilities = classify(
> File "/tmp/Bazel.runfiles_ol4fhm23/runfiles/com_google_deepvariant/deepvariant/small_model/inference.py", line 72, in classify
> return classifier.predict(examples, batch_size=batch_size, verbose=0)
> File "/usr/local/lib/python3.10/dist-packages/keras/src/utils/traceback_utils.py", line 122, in error_handler
> raise e.with_traceback(filtered_tb) from None
> File "/usr/local/lib/python3.10/dist-packages/keras/src/layers/input_spec.py", line 227, in assert_input_compatibility
> raise ValueError(
> ValueError: Input 0 of layer "dense" is incompatible with the layer: expected axis -1 of input shape to have value 70, but received input with shape (1, 106)
> I0604 05:26:50.295563 139989494350272 make_examples_core.py:384] Task 0/2: Writing example info to ./test.examples.tfrecord-00000-of-00002.gz.example_info.json
> I0604 05:26:50.295694 139989494350272 make_examples_core.py:3764] example_shape = None
> I0604 05:26:50.295758 139989494350272 make_examples_core.py:3765] example_channels = [1, 2, 3, 4, 5, 6, 19]
> I0604 05:26:50.296013 139989494350272 make_examples_core.py:384] Task 0/2: Summary stats:
> 0 candidate variants found
> 0 examples written
> 0 candidate variants phased
> 0 small model examples called
> parallel: This job failed:
Have you checked the FAQ? https://github.com/google/deepvariant/blob/r1.10/docs/FAQ.md:
Describe the issue:
When adding phasing arguments to a previously working
make_examplescall it produces an error.Added arguments:
Setup
Steps to reproduce:
relevant subsection
Does the quick start test work on your system?
Please test with https://github.com/google/deepvariant/blob/r0.10/docs/deepvariant-quick-start.md.
Is there any way to reproduce the issue by using the quick start?
Any additional context: