Faster R-CNN Resnet-101-FPN implementation based on TensorFlow 2.0.
- python 3.*
- tensorflow>=2.2.0rc3
- scikit-image
- cv2
-b batch_size (default = 2)
-f finetune (default = 0)
-l learning_rate (default = 1e-4)
-e epochs (default = 100)
-c checkpoint (default = 1 in train_epoch, default = 500 in train_batch)
-n normalization (default = ImageNet's mean and std.)
n = 0: no normalization;
n = 1: Company Articles Dataset's mean and std.
python train_batch.py [commands]- Project Design Documentation
- Records on Debug & Addition of Original Project
- Visualized comparison between different normalization scheme
- Detailed Training and Testing Logs of Training Without Normalization
- Analysis on training result caused by different normalization scheme I
- Analysis on training result caused by different normalization scheme II ☆
- Analysis on training result caused by different anchor ratios
- Comparison with Detectron's Faster RCNN
This work builds on many excellent works, which include:
- Heavily based on tf-eager-fasterrcnn
- matterport/Mask_RCNN
- open-mmlab/mmdetection
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent