Hi!
I was able to train the model with customized datasets but recently when I tried to train the model with pretrained Mask RCNN Res101 weights with last layers deleted, the error "Traceback (most recent call last):
File "tools/train_net.py", line 179, in
main()
File "tools/train_net.py", line 172, in main
model = train(cfg, args.local_rank, args.distributed)
File "tools/train_net.py", line 35, in train
model = build_detection_model(cfg)
File "/srv/home/yliu/newMask/maskrcnn-benchmark/maskrcnn_benchmark/modeling/detector/detectors.py", line 10, in build_detection_model
return meta_arch(cfg)
File "/srv/home/yliu/newMask/maskrcnn-benchmark/maskrcnn_benchmark/modeling/detector/generalized_rcnn.py", line 29, in init
self.backbone = build_backbone(cfg)
File "/srv/home/yliu/newMask/maskrcnn-benchmark/maskrcnn_benchmark/modeling/backbone/backbone.py", line 79, in build_backbone
return registry.BACKBONEScfg.MODEL.BACKBONE.CONV_BODY
File "/srv/home/yliu/newMask/maskrcnn-benchmark/maskrcnn_benchmark/modeling/backbone/backbone.py", line 27, in build_resnet_fpn_backbone
body = resnet.ResNet(cfg)
File "/srv/home/yliu/newMask/maskrcnn-benchmark/maskrcnn_benchmark/modeling/backbone/resnet.py", line 110, in init
stage_with_dcn = cfg.MODEL.RESNETS.STAGE_WITH_DCN[stage_spec.index -1]
File "/srv/home/yliu/anaconda3/envs/mask/lib/python3.6/site-packages/yacs/config.py", line 141, in getattr
raise AttributeError(name)
AttributeError: STAGE_WITH_DCN" occurs.
Any ideas on what's the problem?
❓ Questions and Help
Hi! I was able to train the model with customized datasets but recently when I tried to train the model with pretrained Mask RCNN Res101 weights with last layers deleted, the error "Traceback (most recent call last): File "tools/train_net.py", line 179, in
main()
File "tools/train_net.py", line 172, in main
model = train(cfg, args.local_rank, args.distributed)
File "tools/train_net.py", line 35, in train
model = build_detection_model(cfg)
File "/srv/home/yliu/newMask/maskrcnn-benchmark/maskrcnn_benchmark/modeling/detector/detectors.py", line 10, in build_detection_model
return meta_arch(cfg)
File "/srv/home/yliu/newMask/maskrcnn-benchmark/maskrcnn_benchmark/modeling/detector/generalized_rcnn.py", line 29, in init
self.backbone = build_backbone(cfg)
File "/srv/home/yliu/newMask/maskrcnn-benchmark/maskrcnn_benchmark/modeling/backbone/backbone.py", line 79, in build_backbone
return registry.BACKBONEScfg.MODEL.BACKBONE.CONV_BODY
File "/srv/home/yliu/newMask/maskrcnn-benchmark/maskrcnn_benchmark/modeling/backbone/backbone.py", line 27, in build_resnet_fpn_backbone
body = resnet.ResNet(cfg)
File "/srv/home/yliu/newMask/maskrcnn-benchmark/maskrcnn_benchmark/modeling/backbone/resnet.py", line 110, in init
stage_with_dcn = cfg.MODEL.RESNETS.STAGE_WITH_DCN[stage_spec.index -1]
File "/srv/home/yliu/anaconda3/envs/mask/lib/python3.6/site-packages/yacs/config.py", line 141, in getattr
raise AttributeError(name)
AttributeError: STAGE_WITH_DCN" occurs.
Any ideas on what's the problem?
Thanks a lot for your help!