faster-rcnn.pytorch問題彙總和解決

https://github.com/jwyang/faster-rcnn.pytorch/tree/pytorch-1.0

1、問題：ImportError: cannot import name '_mask' from 'pycocotools' (/faster-rcnn.pytorch/lib/pycocotools/__init__.py)

解決：https://github.com/jwyang/faster-rcnn.pytorch/issues/611

2、問題： from scipy.misc import imread
ImportError: cannot import name 'imread' from 'scipy.misc' (/home/admin/anaconda3/lib/python3.7/site-packages/scipy/misc/__init__.py)

解決：#from scipy.misc import imread
from imageio import imread

3、問題：faster-rcnn.pytorch/lib/model/roi_layers/roi_align.py", line 41, in backward
    sampling_ratio,
RuntimeError: Not implemented on the CPU (ROIAlign_backward at /faster-rcnn.pytorch/lib/model/csrc/ROIAlign.h:44)

解決：python trainval_net.py --cuda

CUDA_VISIBLE_DEVICES=$GPU_ID python trainval_net.py \
                   --dataset pascal_voc --net vgg16 \
                   --bs $BATCH_SIZE --nw $WORKER_NUMBER \
                   --lr $LEARNING_RATE --lr_decay_step $DECAY_STEP \
                   --cuda

4、問題：

[session 1][epoch  9][iter  300/ 302] loss: nan, lr: 1.00e-04
            fg/bg=(256/0), time cost: 26.321015
            rpn_cls: nan, rpn_box: nan, rcnn_cls: nan, rcnn_box nan
save model: models/vgg16/pascal_voc/faster_rcnn_1_9_301.pth
[session 1][epoch 10][iter    0/ 302] loss: nan, lr: 1.00e-04
            fg/bg=(256/0), time cost: 0.186927
            rpn_cls: nan, rpn_box: nan, rcnn_cls: nan, rcnn_box nan
[session 1][epoch 10][iter  100/ 302] loss: nan, lr: 1.00e-04
            fg/bg=(256/0), time cost: 30.308010
            rpn_cls: nan, rpn_box: nan, rcnn_cls: nan, rcnn_box nan
[session 1][epoch 10][iter  200/ 302] loss: nan, lr: 1.00e-04
            fg/bg=(256/0), time cost: 26.225091
            rpn_cls: nan, rpn_box: nan, rcnn_cls: nan, rcnn_box nan
[session 1][epoch 10][iter  300/ 302] loss: nan, lr: 1.00e-04
            fg/bg=(256/0), time cost: 25.555755
            rpn_cls: nan, rpn_box: nan, rcnn_cls: nan, rcnn_box nan
save model: models/vgg16/pascal_voc/faster_rcnn_1_10_301.pth
[session 1][epoch 11][iter    0/ 302] loss: nan, lr: 1.00e-04
            fg/bg=(256/0), time cost: 1.063025
            rpn_cls: nan, rpn_box: nan, rcnn_cls: nan, rcnn_box nan

解決：

 

訓練中：

[session 1][epoch  1][iter 1400/10022] loss: 0.9442, lr: 1.00e-03
            fg/bg=(64/192), time cost: 34.894407
            rpn_cls: 0.1092, rpn_box: 0.0959, rcnn_cls: 0.7647, rcnn_box 0.5711
[session 1][epoch  1][iter 1500/10022] loss: 0.8075, lr: 1.00e-03
            fg/bg=(40/216), time cost: 34.486090
            rpn_cls: 0.1273, rpn_box: 0.1090, rcnn_cls: 0.2956, rcnn_box 0.3665
[session 1][epoch  1][iter 1600/10022] loss: 0.9427, lr: 1.00e-03
            fg/bg=(59/197), time cost: 34.548775
            rpn_cls: 0.2252, rpn_box: 0.1195, rcnn_cls: 0.4307, rcnn_box 0.6220
[session 1][epoch  1][iter 1700/10022] loss: 0.8819, lr: 1.00e-03
            fg/bg=(14/242), time cost: 34.917199
            rpn_cls: 0.2402, rpn_box: 0.1786, rcnn_cls: 0.2142, rcnn_box 0.1220
[session 1][epoch  1][iter 1800/10022] loss: 0.8147, lr: 1.00e-03
            fg/bg=(22/234), time cost: 34.602410
            rpn_cls: 0.0794, rpn_box: 0.0630, rcnn_cls: 0.1504, rcnn_box 0.2089

繼續調優：