Skip to content

Instantly share code, notes, and snippets.

@f-rumblefish

f-rumblefish/YOLOv3 Checklist.csv

Last active June 17, 2019 02:21
Show Gist options
  • Save f-rumblefish/061e211ebcd5dd6fe0e0de93d482c580 to your computer and use it in GitHub Desktop.
Save f-rumblefish/061e211ebcd5dd6fe0e0de93d482c580 to your computer and use it in GitHub Desktop.
Download ZIP
A Checklist for Training YOLOv3
Raw
YOLOv3 Checklist.csv
0. Source https://github.com/qqwweee/keras-yolo3
1. Training 1.1. create mydata_train.txt ref: train.txt
1.2. create mydata_class.txt ref: model_data/voc_classes.txt
1.3. change train.py to train_mydata.py 1.3.1. annotation_path = 'mydata_train.txt' ref: 1.1
1.3.2. classes_path = 'model_data/mydata_classes.txt' ref: 1.2
1.3.3. create_model with load_pretrained=False optional (if pre-trained weight doesn't work)
1.3.4. model.save('mymodel.h5') save model and weight for prediction
1.3.5. change epochs from 50 to 5 optional (check if it works or not)
1.3.6. change batch_size from 32 to 8 optional (if it has some memory problems)
1.3.7. remove training in the second stage optional (if the first stage is without pre-trained weight)
1.4. python train_mydata.py
2. Detection 2.1 change yolo.py 2.1.1. change model_path to 'mymodel.h5' ref: 1.3.4
2.1.2. change classes_path to 'model_data/mydata_classes.txt' ref: 1.3.2
2.1.3. change score to 0.0 optional (for debug/if no object is detected)
2.2 python yolo_video.py --image
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment