Skip to content

Flow to train the model. #9

@talk2sohail

Description

@talk2sohail

Hi there,

I am trying to train the CNN model but I am not able to prepare the dataset. Can you please help with the flow or steps to be specific in order to achieve the above said purpose. I urge u to please let me know if it can done. My aim is to score protein-protein interaction.

Steps I have done so far:

  1. Tried running the train.py with pointclouds.h5 file but I am getting the following error:
    cmd : python3 scripts/train.py --data_path pointclouds.h5 --optimizer SGD
    output :
    Traceback (most recent call last): File "scripts/train.py", line 64, in <module> dataloader = data.DataLoader(dataset, batch_size=arg.batch_size, shuffle=True, num_workers=1) File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/dataloader.py", line 266, in __init__ sampler = RandomSampler(dataset, generator=generator) # type: ignore File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/sampler.py", line 104, in __init__ "value, but got num_samples={}".format(self.num_samples)) ValueError: num_samples should be a positive integer value, but got num_samples=0

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions