Closed atger closed 3 years ago
The model file path should be /path/to/model.GATC.R9_2D.tem.puc19.bn17.sn360/bn_17.sn_360.epoch_5.ckpt
.
Best, Peng
Given path as suggested.
Still getting error:
Traceback (most recent call last): File "/mnt/storage3/anand/programs/miniconda3/envs/deepsignalenv/lib/python3.6/multiprocessing/process.py", line 258, in _bootstrap self.run() File "/mnt/storage3/anand/programs/miniconda3/envs/deepsignalenv/lib/python3.6/multiprocessing/process.py", line 93, in run self._target(*self._args, **self._kwargs) File "/mnt/storage3/anand/programs/miniconda3/envs/deepsignalenv/lib/python3.6/site-packages/deepsignal-0.1.8-py3.6.egg/deepsignal/call_modifications.py", line 217, in _fast5s_q_to_pred_str_q saver.restore(sess, model_path) File "/mnt/storage3/anand/programs/miniconda3/envs/deepsignalenv/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1268, in restore
On Tue, Apr 13, 2021 at 5:11 PM Peng Ni @.***> wrote:
The model file path should be /path/to/model.GATC.R9_2D.tem.puc19.bn17.sn360/bn_17.sn_360.epoch_5.ckpt.
Best, Peng
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/bioinfomaticsCSU/deepsignal/issues/70#issuecomment-818669367, or unsubscribe https://github.com/notifications/unsubscribe-auth/AEWPKKCLPPUME2PBJT3I3D3TIQUWZANCNFSM423FB2LA .
I'm not sure that if the last dot was included, but it should NOT be. It should be /path/to/model.GATC.R9_2D.tem.puc19.bn17.sn360/bn_17.sn_360.epoch_5.ckpt
, also, --motifs
should be set to GATC
, and --mod_loc
should be set to 1
.
Best, Peng
Again thrown error:
Traceback (most recent call last): File "/mnt/storage3/anand/programs/miniconda3/envs/deepsignalenv/lib/python3.6/multiprocessing/process.py", line 258, in _bootstrap self.run() File "/mnt/storage3/anand/programs/miniconda3/envs/deepsignalenv/lib/python3.6/multiprocessing/process.py", line 93, in run self._target(*self._args, **self._kwargs) File "/mnt/storage3/anand/programs/miniconda3/envs/deepsignalenv/lib/python3.6/site-packages/deepsignal-0.1.8-py3.6.egg/deepsignal/call_modifications.py", line 217, in _fast5s_q_to_pred_str_q saver.restore(sess, model_path) File "/mnt/storage3/anand/programs/miniconda3/envs/deepsignalenv/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1292, in restore err, "a Variable name or other graph key that is missing") tensorflow.python.framework.errors_impl.NotFoundError: Restoring from checkpoint failed. This is most likely due to a Variable name or other graph key that is missing from the checkpoint. Please ensure that you have not altered the graph expected based on the checkpoint. Original error:
Key modelem/bw/multi_rnn_cell/cell_0/lstm_cell/bias not found in checkpoint [[node save/RestoreV2 (defined at /mnt/storage3/anand/programs/miniconda3/envs/deepsignalenv/lib/python3.6/site-packages/deepsignal-0.1.8-py3.6.egg/deepsignal/call_modifications.py:216) ]]
Caused by op 'save/RestoreV2', defined at:
File
"/mnt/storage3/anand/programs/miniconda3/envs/deepsignalenv/bin/deepsignal",
line 33, in
NotFoundError (see above for traceback): Restoring from checkpoint failed. This is most likely due to a Variable name or other graph key that is missing from the checkpoint. Please ensure that you have not altered the graph expected based on the checkpoint. Original error:
Key modelem/bw/multi_rnn_cell/cell_0/lstm_cell/bias not found in checkpoint [[node save/RestoreV2 (defined at /mnt/storage3/anand/programs/miniconda3/envs/deepsignalenv/lib/python3.6/site-packages/deepsignal-0.1.8-py3.6.egg/deepsignal/call_modifications.py:216) ]]
On Tue, Apr 13, 2021 at 7:23 PM Peng Ni @.***> wrote:
I'm not sure that if the last dot was included, but it should NOT be. It should be /path/to/model.GATC.R9_2D.tem.puc19.bn17.sn360/bn_17.sn_360.epoch_5.ckpt, also, --motifs should be set to GATC, and --mod_loc should be set to 1.
Best, Peng
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/bioinfomaticsCSU/deepsignal/issues/70#issuecomment-818754171, or unsubscribe https://github.com/notifications/unsubscribe-auth/AEWPKKG4NYRQBEDRBDVQEKDTIREGFANCNFSM423FB2LA .
Sorry that I did not notice the version before. GATC model is suited for deepsignal<=0.1.6
as README said. So trying to reinstall deepsignal with a lower version may work.
Best, Peng
Older version throwing following error:
Illegal instruction (core dumped)
Is it possible to provide GATC model for latest version?
@atger , thanks very much for your interest of deepsignal. Unfortunately we can not re-train GATC model, cause we have lost the data from signalAlign used for training.
Also, I didn't reproduce the 'Illegal instruction (core dumped)' error in my own test. Here's the environment I used for deepsignal==0.1.6:
Package Version
--------------- ----------
absl-py 0.6.1
astor 0.7.1
bleach 1.5.0
certifi 2018.11.29
cycler 0.10.0
Cython 0.29
deepsignal 0.1.6
future 0.17.1
gast 0.2.0
grpcio 1.16.1
h5py 2.8.0
html5lib 0.9999999
Jinja2 2.10
kiwisolver 1.0.1
mappy 2.14
Markdown 3.0.1
MarkupSafe 1.1.0
matplotlib 3.0.2
mkl-fft 1.0.6
mkl-random 1.0.2
numpy 1.15.4
ont-tombo 1.5
pandas 0.23.4
patsy 0.5.1
pip 18.1
protobuf 3.6.1
pyfaidx 0.5.5.2
pyparsing 2.3.1
python-dateutil 2.7.5
pytz 2018.7
rpy2 2.9.1
scikit-learn 0.20.1
scipy 1.1.0
setuptools 40.6.2
six 1.12.0
statsmodels 0.9.0
tensorboard 1.8.0
tensorflow 1.8.0
termcolor 1.1.0
tqdm 4.7.2
Werkzeug 0.14.1
wheel 0.32.3
And the command is:
deepsignal call_mods --input_path BJXWZ_SUP.07C123.albacore/workspace/pass/30 --model_path model.GATC.R9_2D.tem.puc19.bn17.sn360/bn_17.sn_360.epoch_5.ckpt --result_file test.GATC.call_mods.txt --reference_path /homeb/nipeng/data/genome/human/GRCh38.primary_assembly.genome.fa --motifs GATC --mod_loc 1 --nproc 40 --corrected_group RawGenomeCorrected_001
Hope that can help you!
Best, Peng
Hi Peng,
Thank you so much for the great work and support. I was wondering if you could provide an environment for my reference to run the plasmid model on a GPU please? I attempted different versions of tf, deepsignal but failed to use GPU.
@edwwlui , Here's the environment (Python==3.6.7) for reference:
Package Version
--------------- ----------
deepsignal 0.1.6
h5py 2.8.0
numpy 1.15.4
ont-tombo 1.5
pandas 0.23.4
pip 18.1
scikit-learn 0.20.1
scipy 1.1.0
statsmodels 0.9.0
tensorboard 1.8.0
tensorflow 1.8.0
To use GPU, pip install tensorflow-gpu==1.8.0
should be run before installing deepsignal.
And the command to run deepsignal should be like:
CUDA_VISIBLE_DEVICES=0 deepsignal call_mods --input_path BJXWZ_SUP.07C123.albacore/workspace/pass/30 --model_path model.GATC.R9_2D.tem.puc19.bn17.sn360/bn_17.sn_360.epoch_5.ckpt --result_file test.GATC.call_mods.txt --reference_path /homeb/nipeng/data/genome/human/GRCh38.primary_assembly.genome.fa --motifs GATC --mod_loc 1 --nproc 40 --corrected_group RawGenomeCorrected_001 --is_gpu yes
Hope this can help!
Best, Peng
appreciate it, it works
DataLossError (see above for traceback): Unable to open table file /mnt/storage3/anand/SO_9407/methylation_calling/models/model.GATC.R9_2D.tem.puc19.bn17.sn360: Data loss: file is too short to be an sstable: perhaps your file is in a different file format and you need to use a different restore operator? [[node save/RestoreV2 (defined at /mnt/storage3/anand/programs/miniconda3/envs/deepsignalenv/lib/python3.6/site-packages/deepsignal-0.1.8-py3.6.egg/deepsignal/call_modifications.py:216) ]]
2021-04-13 17:02:48.652716: W tensorflow/core/util/tensor_slice_reader.cc:95] Could not open /mnt/storage3/anand/SO_9407/methylation_calling/models/model.GATC.R9_2D.tem.puc19.bn17.sn360: Data loss: file is too short to be an sstable: perhaps your file is in a different file format and you need to use a different restore operator? 2021-04-13 17:02:48.658680: W tensorflow/core/util/tensor_slice_reader.cc:95] Could not open /mnt/storage3/anand/SO_9407/methylation_calling/models/model.GATC.R9_2D.tem.puc19.bn17.sn360: Data loss: file is too short to be an sstable: perhaps your file is in a different file format and you need to use a different restore operator? 2021-04-13 17:02:48.658806: W tensorflow/core/framework/op_kernel.cc:1401] OP_REQUIRES failed at save_restore_tensor.cc:175 : Data loss: Unable to open table file /mnt/storage3/anand/SO_9407/methylation_calling/models/model.GATC.R9_2D.tem.puc19.bn17.sn360: Data loss: file is too short to be an sstable: perhaps your file is in a different file format and you need to use a different restore operator? Process Process-1: Traceback (most recent call last): File "/mnt/storage3/anand/programs/miniconda3/envs/deepsignalenv/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1334, in _do_call return fn(*args) File "/mnt/storage3/anand/programs/miniconda3/envs/deepsignalenv/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1319, in _run_fn options, feed_dict, fetch_list, target_list, run_metadata) File "/mnt/storage3/anand/programs/miniconda3/envs/deepsignalenv/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1407, in _call_tf_sessionrun run_metadata) tensorflow.python.framework.errors_impl.DataLossError: Unable to open table file /mnt/storage3/anand/SO_9407/methylation_calling/models/model.GATC.R9_2D.tem.puc19.bn17.sn360: Data loss: file is too short to be an sstable: perhaps your file is in a different file format and you need to use a different restore operator? [[{{node save/RestoreV2}}]]