machine-learning-deep-learning/Machine-Learning-Collection
1
0
Fork 0
mirror of https://github.com/aladdinpersson/Machine-Learning-Collection.git synced 2026-02-21 11:18:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Aladdin Persson
2021-03-08 23:57:45 +01:00
committed by GitHub
parent 91b1fd156c
commit 0506a2a878
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
ML/Pytorch/object_detection/YOLOv3/README.md
View File

@@ -14,7 +14,7 @@ $ pip install requirements.txt
Available on Kaggle: [link](https://www.kaggle.com/dataset/1cf520aba05e023f2f80099ef497a8f3668516c39e6f673531e3e47407c46694) Available on Kaggle: [link](https://www.kaggle.com/dataset/1cf520aba05e023f2f80099ef497a8f3668516c39e6f673531e3e47407c46694)
### Download Pascal VOC dataset ### Download Pascal VOC dataset
Download the preprocessed dataset from [link](https://www.kaggle.com/aladdinpersson/pascal-voc-yolo-works-with-albumentations). Just unzip this in the main directory. Download the preprocessed dataset from [link](https://www.kaggle.com/aladdinpersson/pascal-voc-dataset-used-in-yolov3-video). Just unzip this in the main directory.
### Download MS COCO dataset ### Download MS COCO dataset
Download the preprocessed dataset from [coming soon](). Just unzip this in the main directory. Download the preprocessed dataset from [coming soon](). Just unzip this in the main directory.
@@ -26,7 +26,7 @@ Edit the config.py file to match the setup you want to use. Then run train.py
| Model | mAP @ 50 IoU | | Model | mAP @ 50 IoU |
| ----------------------- |:-----------------:| | ----------------------- |:-----------------:|
| YOLOv3 (Pascal VOC) | 78.2 | | YOLOv3 (Pascal VOC) | 78.2 |
| YOLOv3 (MS-COCO) | Not done yet | | YOLOv3 (MS-COCO) | Will probably train on this at some point |
The model was evaluated with confidence 0.2 and IOU threshold 0.45 using NMS. The model was evaluated with confidence 0.2 and IOU threshold 0.45 using NMS.
@@ -54,4 +54,4 @@ We present some updates to YOLO! We made a bunch of little design changes to mak
journal = {arXiv}, journal = {arXiv},
year={2018} year={2018}
} }
``` ```