You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+5Lines changed: 5 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -3,8 +3,13 @@ Analysis for Kaggle Human Protein Atlas Single Cell Classification challenge
3
3
4
4
This repo is for analysis of the [HPA Single Cell Classification](https://www.kaggle.com/c/hpa-single-cell-image-classification) results.
5
5
6
+
## Content
6
7
This includes
7
8
* Average Precision scores for each class and Jaccard index (IOU) of each submission at per cell level in `class_scoring` and `segmentation_matching`. This is scored using Tensorflow Object Detection API under Apache license. Specifically, scoring is done with [oid_hpasc_challenge_evaluation.py](models/research/object_detection/metrics/oid_hpasc_challenge_evaluation.py) and [oid_hpasc_challenge_evaluation_test.py](models/research/object_detection/metrics/oid_hpasc_challenge_evaluation_test.py) for testing.
8
9
* Analysis scripts as described in the manuscript in `analysis`
9
10
* Winner solution (`team1_bestfitting`) including model and analysis code provided by Shubin Dai (bestfitting) and modified by Trang Le for analysis and prediction.
10
11
*`plot` contains plotting this competition's metadata obtained from [Meta Kaggle](https://www.kaggle.com/kaggle/meta-kaggle).
0 commit comments