Crash during ptp_split

[DradeAW]

When running yass, the sample test worked, but it didn't with my data. I run yass without a neural network for spike detections. Here is the error:

yass.pipeline@run 30/03/2020 11:55:06 INFO YASS version: 2.0 yass.preprocess.run@run 30/03/2020 11:55:06 INFO # of chunks: 184 yass.preprocess.run@run 30/03/2020 11:55:06 INFO Temporary folder tmp/preprocess already exists, output will be stored there yass.preprocess.run@run 30/03/2020 11:55:06 INFO Output dtype for transformed data will be float32 yass.pipeline@initial_block 30/03/2020 11:55:06 INFO INITIAL DETECTION yass.pipeline@initial_block 30/03/2020 11:55:06 INFO INITIAL CLUSTERING inpput to block2: tmp/block_1/cluster_post_process/templates.npy yass.pipeline@iterative_block 30/03/2020 11:55:06 INFO DECONV yass.pipeline@iterative_block 30/03/2020 11:55:06 INFO RESIDUAL COMPUTATION yass.pipeline@iterative_block 30/03/2020 11:55:06 INFO RECLUSTERING yass.cluster.run@run 30/03/2020 11:55:06 INFO Split on PTP yass.cluster.ptp_split@run_split_on_ptp 30/03/2020 11:55:06 INFO Get Spike PTP 100%|███████████████████████████████████████████| 60/60 [00:02<00:00, 24.47it/s] Traceback (most recent call last): File "/users/nsr/wyngaard/miniconda3/envs/yass2/bin/yass", line 11, in load_entry_point('yass-algorithm', 'console_scripts', 'yass')() File "/users/nsr/wyngaard/miniconda3/envs/yass2/lib/python3.7/site-packages/click/core.py", line 829, in call return self.main(args, kwargs) File "/users/nsr/wyngaard/miniconda3/envs/yass2/lib/python3.7/site-packages/click/core.py", line 782, in main rv = self.invoke(ctx) File "/users/nsr/wyngaard/miniconda3/envs/yass2/lib/python3.7/site-packages/click/core.py", line 1259, in invoke return _process_result(sub_ctx.command.invoke(sub_ctx)) File "/users/nsr/wyngaard/miniconda3/envs/yass2/lib/python3.7/site-packages/click/core.py", line 1066, in invoke return ctx.invoke(self.callback, ctx.params) File "/users/nsr/wyngaard/miniconda3/envs/yass2/lib/python3.7/site-packages/click/core.py", line 610, in invoke return callback(args, **kwargs) File "/export/home1/users/nsr/wyngaard/yass/src/yass/command_line.py", line 80, in sort calculate_rf=calculate_rf, visualize=visualize)#, File "/export/home1/users/nsr/wyngaard/yass/src/yass/pipeline.py", line 162, in run run_chunk_sec = CONFIG.clustering_chunk) File "/export/home1/users/nsr/wyngaard/yass/src/yass/pipeline.py", line 362, in iterative_block full_run=True) File "/export/home1/users/nsr/wyngaard/yass/src/yass/cluster/run.py", line 156, in run denoiser) File "/export/home1/users/nsr/wyngaard/yass/src/yass/cluster/ptp_split.py", line 59, in run_split_on_ptp ptp_raw, ptp_deno = getcleanptp.compute_ptps() File "/export/home1/users/nsr/wyngaard/yass/src/yass/cluster/getptp.py", line 255, in compute_ptps del dat, idx_in, spike_index_batch, t_index, c_index, residuals, wfs, denoised_wfs UnboundLocalError: local variable 'denoised_wfs' referenced before assignment

I tried debugging this on my own, and tried to get rid of the del denoised_wfs. When I did that, I got the same error, but with the variable 'ptps_denoised'. I found out that all self.denoiser are None, could this be what's causing the issue?

Thank you

[jinhyunglee]

hi have you pulled the latest code?

[DradeAW]

Hi,

Yes, I use Yass 2.0 (installed friday March 27th) with cuda 10.2 on Ubuntu 18.04.

[jinhyunglee]

can you check if it fixed the problem?

have you tried to use nn models? I can direct you with training neural nets (it is very simple!)

[DradeAW]

Thank you very much! It works fine now!

I want to compare when using the nn model vs not using it. I already know how to train it, but thank you!