Skip to content

Latest commit

 

History

History
60 lines (35 loc) · 1.41 KB

README.md

File metadata and controls

60 lines (35 loc) · 1.41 KB

Thông tin cuộc thi iWildCam_2019_FGVC6:

Top 3% (7/336) solution for iWildCam 2019 competition (Categorize animals in the wild), which is as part of the FGVC6 workshop at CVPR 2019

Thanks to my team members!

Please view the detailed report Efficient Method for Categorize Animals in the Wild.

Requirements

  • Python 3.6
  • pytorch 1.1.0

About the Code

1. Prepare Data

Download the competition data according to here

After downloading, save the image-file name as CSV format.

python prep_data.py

2. Detect and Crop the Image

python detect_crop_image.py

In my method, I first run object detection and crop the bounding box, then use the cropped image for classification.

3. Train the Model

python train_model.py

4. Prediction

python infer.py

About the Method

I got the best single model prediction result (f1=0.224 in private LB) with the following configuration:

model: efficientnet_b0 (imagenet pretrained)

image augmentation: traditional image augmentation + CLAHE + gray scale + cutout + mixup + label smoothing

Thực tập dự án tốt nghiệp HCMUS 2022

Code bài báo /

YOLO: /yolo

Faster-RCNN: /tensorpack/examples/FasterRCNN