SBD Train & Test
| Model | [email protected] (Original [1]) | [email protected] (Original [1]) | [email protected] (weight conversion) | [email protected] (weight conversion) | [email protected] (train) | [email protected] (train) |
|---|---|---|---|---|---|---|
| FCIS ResNet101 | 65.7 | 52.1 | 64.2 | 51.2 | 64.1 (1 GPU) | 51.2 (1 GPU) |
Segment objects in an given image. This demo downloads SBD pretrained model automatically if a pretrained model path is not given.
python demo.py [--gpu <gpu>] [--pretrained-model <model_path>] <image.jpg>The evaluation can be conducted using chainercv/examples/instance_segmentation/eval_sbd.py
You can train the model with the following code.
Note that this code requires SciPy module.
python train.py [--gpu <gpu>]If you want to use multiple GPUs, use train_multi.py.
Note that this code requires chainermn module.
mpi4exec -n <n_gpu> python train_multi.py --lr <n_gpu>*0.0005
You can download weights that were trained by ChainerCV.
Convert *.params to *.npz.
Note that the number of classes and network structure is specified by --dataset.
python mxnet2npz.py [--dataset sbd|coco] [--out <npz filename>] <param filename>- Yi Li et al. "Fully Convolutional Instance-aware Semantic Segmentation" CVPR 2017.