search

ersilia-os / eos46ev

GNU General Public License v3.0
0 stars 1 forks source link

New model ready for testing! #5

Closed github-actions[bot] closed 1 year ago

github-actions[bot] commented 1 year ago

This model is ready for testing. If you are assigned to this issue, please try it out using the CLI, Google Colab and DockerHub and let us know if it works!

simrantan commented 1 year ago

@GemmaTuron

The model worked on Colab and Docker perfectly fine, but i ran into an error on CLI(details below) when running eml_canonical. When running a single input, it ran fine (file also included below) Docker: Log eos46ev_docker_log.txt Output eos46ev_docker_output.txt

CLI: Log eos46evout.log Output: ERROR: errorCLIeos46ev.txt Normal Output: CLIoutputeos46ev.txt

Colab: Log eos46evcolab.log

Output

samuelmaina commented 1 year ago

@ZakiaYahya and @GemmaTuron , Fetched successfully for both cli and colab and able to predict for one input in both. For input files, I am getting status 500 for many of the smiles and a few 200. I run on colab to completion and the output produced had a close to empty probability column (since most smiles produced 500 status) with very few smiles having vals. In the cli, after 350ish smiles producing a status of 500, this error occurred which broke the prediction,

Traceback (most recent call last):
  File "/home/samuelmayna/miniconda3/envs/ersilia/bin/ersilia", line 33, in <module>
    sys.exit(load_entry_point('ersilia', 'console_scripts', 'ersilia')())
  File "/home/samuelmayna/miniconda3/envs/ersilia/lib/python3.7/site-packages/click/core.py", line 1130, in __call__
    return self.main(*args, **kwargs)
  File "/home/samuelmayna/miniconda3/envs/ersilia/lib/python3.7/site-packages/click/core.py", line 1055, in main
    rv = self.invoke(ctx)
  File "/home/samuelmayna/miniconda3/envs/ersilia/lib/python3.7/site-packages/click/core.py", line 1657, in invoke
    return _process_result(sub_ctx.command.invoke(sub_ctx))
  File "/home/samuelmayna/miniconda3/envs/ersilia/lib/python3.7/site-packages/click/core.py", line 1404, in invoke
    return ctx.invoke(self.callback, **ctx.params)
  File "/home/samuelmayna/miniconda3/envs/ersilia/lib/python3.7/site-packages/click/core.py", line 760, in invoke
    return __callback(*args, **kwargs)
  File "/home/samuelmayna/miniconda3/envs/ersilia/lib/python3.7/site-packages/bentoml/cli/click_utils.py", line 138, in wrapper
    return func(*args, **kwargs)
  File "/home/samuelmayna/miniconda3/envs/ersilia/lib/python3.7/site-packages/bentoml/cli/click_utils.py", line 115, in wrapper
    return_value = func(*args, **kwargs)
  File "/home/samuelmayna/miniconda3/envs/ersilia/lib/python3.7/site-packages/bentoml/cli/click_utils.py", line 99, in wrapper
    return func(*args, **kwargs)
  File "/home/samuelmayna/ersilia/ersilia/cli/commands/run.py", line 34, in run
    result = mdl.run(input=input, output=output, batch_size=batch_size)
  File "/home/samuelmayna/ersilia/ersilia/core/model.py", line 143, in _method
    return self.api(api_name, input, output, batch_size)
  File "/home/samuelmayna/ersilia/ersilia/core/model.py", line 353, in api
    api_name=api_name, input=input, output=output, batch_size=batch_size
  File "/home/samuelmayna/ersilia/ersilia/core/model.py", line 367, in api_task
    for r in result:
  File "/home/samuelmayna/ersilia/ersilia/core/model.py", line 194, in _api_runner_iter
    for result in api.post(input=input, output=output, batch_size=batch_size):
  File "/home/samuelmayna/ersilia/ersilia/serve/api.py", line 320, in post
    input=unique_input, output=None, batch_size=batch_size
  File "/home/samuelmayna/ersilia/ersilia/serve/api.py", line 296, in post_unique_input
    for res in self.post_amenable_to_h5(input, output, batch_size):
  File "/home/samuelmayna/ersilia/ersilia/serve/api.py", line 262, in post_amenable_to_h5
    done_input, todo_input, done_output, todo_output
  File "/home/samuelmayna/ersilia/ersilia/serve/api.py", line 208, in _process_done_todo_results
    yield todo_output_data[i]
IndexError: list index out of range

I did not test for docker since I highly doubt it will be correct if both cli and colab have some errors. Here are the fetch and prediction logs and outputs for both .

GemmaTuron commented 1 year ago

@ZakiaYahya

It seems that some molecules fail to process and then the model is unable to return the appropriate number of outputs? We have done modifications to the Ersilia codebase, so could you try to run the eml file with the newest Ersilia code?

ZakiaYahya commented 1 year ago

Hello @GemmaTuron Right, i'll pull the the latest version of ersilia and then test it with eml_canonical file. Will let you know as soon as possible. Thanks.

GemmaTuron commented 1 year ago

@samuelmaina

Zakia has been working to ensure the model is fine. Could you please check this latest version? Thanks

samuelmaina commented 1 year ago

@GemmaTuron , The model is producing probabilities for all the eml dataset and for individual smiles

CLI