Training my own dataset
Nobody has claimed this yet.
Assessment
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Newbie friendliness
- 30/100
- Issue type
- Documentation
- Clarity
- Needs clarification
- Activity status
- Stale
- Domain
- data, documentation, machine-learning
Research direction
Start by reviewing the data\cath directory and the issue's distinction between PDB files and the expected Dataset format. Document the required dataset structure, how compatibility is determined, and the steps for training on a custom dataset. Done means a newcomer can prepare compatible data and follow the training process without needing an unanswered explanation.
Written by the indexing model from the issue text.
Description
Hi, thank you for sharing your very interesting folding model!
I want to train a model using my own dataset. Do I just need to put the dataset in the data\cath directory? Also, I would appreciate it if you could explain how to create a compatible Dataset. It seems like PDB files are not compatible.
- Dominant language
- Jupyter Notebook
- Stars
- 568
- Forks
- 74
- Avg merge
- 20h 2m
- Merged PRs (30d)
- 1
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from microsoft/foldingdiff
-
Difficulty 4/5 3-5 days Newbie friendliness 38/100
microsoft/foldingdiff#32 ·
-
Difficulty 4/5 3-5 days Newbie friendliness 30/100
microsoft/foldingdiff#28 · 1 comment ·
-
Difficulty 5/5 Over a week Newbie friendliness 20/100
microsoft/foldingdiff#26 ·
-
Difficulty 1/5 Under an hour Newbie friendliness 20/100
microsoft/foldingdiff#25 ·
-
Difficulty 4/5 3-5 days Newbie friendliness 25/100
microsoft/foldingdiff#24 ·
All issues in microsoft/foldingdiff
Similar issues
-
bug triage
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
fivetran/great_expectations#12253 ·
-
Difficulty 2/5 1-3 hours Newbie friendliness 75/100
-
correction metadata
Difficulty 1/5 Under an hour Newbie friendliness 78/100
acl-org/acl-anthology#10071 · 1 comment ·
-
data:css needs triage
Difficulty 2/5 1-3 hours Newbie friendliness 75/100
mdn/browser-compat-data#30618 ·
-
Difficulty 2/5 1-3 hours Newbie friendliness 70/100
basedosdados/pipelines#2095 ·