MLBazaar / MLBazaar/mit-d3m

Missing metric for objectDetectionAP

Open
#18 0 comments 0 reactions 1 assignee View on GitHub

@csala is already working on this.

Since May 24, 2020.

Dominant language
Python
Stars
8
Forks
7
PR merge metrics
No merged PRs in 30d

Description

  • mit-d3m version: 0.2.1
  • Python version: 3.6.8
  • Operating System: macOS 10.15.4
Description

Trying to load LL1_penn_fudan_pedestrian, but get error that there is no metric for objectDetectionAP

What I Did
import mit_d3m
mit_d3m.load_dataset('LL1_penn_fudan_pedestrian')
/usr/local/miniconda3/envs/mlz/lib/python3.6/site-packages/mit_d3m/dataset.py:71: UserWarning: the datasetSchemaVersions in the API and datasetDoc do not match!
  warnings.warn("the datasetSchemaVersions in the API and datasetDoc do not match!")
/usr/local/miniconda3/envs/mlz/lib/python3.6/site-packages/mit_d3m/dataset.py:227: UserWarning: the problemSchemaVersions in the API and datasetDoc do not match!
  warnings.warn("the problemSchemaVersions in the API and datasetDoc do not match!")
---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
<ipython-input-9-a51e1c460555> in <module>
----> 1 mit_d3m.load_dataset('LL1_penn_fudan_pedestrian')

/usr/local/miniconda3/envs/mlz/lib/python3.6/site-packages/mit_d3m/__init__.py in load_dataset(dataset, root, force_download)
    150 
    151     dataset = loader.load(d3mds)
--> 152     dataset.scorer = METRICS_DICT[d3mds.get_metric()]
    153 
    154     return dataset

KeyError: 'objectDetectionAP'

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.