ruoqianguo/cascade-rcnn_Pytorch

Issues

• can't find model.utils.cython_bbox

  #52 opened 4 years ago by ccjchun
  3

• Multiple GPU fail if not set CUDA_VISIBLE_DEVICES

  #22 opened 3 years ago by hopeisme
  0

• cudaCheckError() failed : an illegal memory access was encountered

  #10 opened 6 years ago by KevinQian97
  12

• Traceback (most recent call last): File "trainval_net.py", line 263, in <module> im_data = im_data.cuda() File "/root/miniconda3/lib/python3.6/site-packages/torch/_utils.py", line 66, in _cuda return new_type(self.size()).copy_(self, async) File "/root/miniconda3/lib/python3.6/site-packages/torch/cuda/__init__.py", line 266, in _lazy_new _lazy_init() File "/root/miniconda3/lib/python3.6/site-packages/torch/cuda/__init__.py", line 85, in _lazy_init torch._C._cuda_init() RuntimeError: cuda runtime error (38) : no CUDA-capable device is detected at /opt/conda/conda-bld/pytorch_1511286954179/work/torch/lib/THC/THCGeneral.c:70

  #51 opened 4 years ago by aiyodiulehuner
  0

• RuntimeError: The size of tensor a (900) must match the size of tensor b (300) at non-singleton dimension 1

  #50 opened 4 years ago by weixiangzhan
  0

• how to speed up training process

  #36 opened 6 years ago by wyxhahaha
  1

• Has anyone successfully run this program

  #47 opened 5 years ago by luckyxianxian
  3

• ImportError: torch.utils.ffi is deprecated. Please use cpp extensions instead.

  #43 opened 5 years ago by 17320266033
  4

• [solution of errors]'the dim of decoded rois' and'illegal memory acecess'

  #49 opened 4 years ago by Jacky-gsq
  0

• torch version problem

  #48 opened 5 years ago by EillotY
  2

• Does anyone try this code on COCO dataset?

  #44 opened 5 years ago by distillation-dcf
  1

• rpn_box: 0.0000

  #39 opened 6 years ago by luyaozhi
  1

• ValueError: operands could not be broadcast together with shapes (1216,800,4) (1,1,3) (1216,800,4)

  #21 opened 6 years ago by yuyijie1995
  1

• sh make.sh error

  #46 opened 5 years ago by Damon2019
  0

• IndexError: Indexing a Tensor with a torch.cuda.LongTensor triggers index_select semantics, and thus we expect a vector, but the indexing Tensor passed has 0 dimensions

  #45 opened 5 years ago by Lydaidai
  0

• KeyError: 'boxes'

  #42 opened 6 years ago by deyiwang89
  2

• sh make.sh error

  #41 opened 6 years ago by Tuyota
  2

• Do the three stages of Cascade RCNN share the same set of parameters?

  #40 opened 6 years ago by JoyHuYY1412
  0

• 段错误（吐核）

  #38 opened 6 years ago by wddwzwhhxx
  0

• return nll_loss Error

  #4 opened 6 years ago by yuyijie1995
  1

• Can you share your trained model in other cloud storage, like baiduyun? Thanks

  #37 opened 6 years ago by lyatdawn
  0

• RuntimeError: cuda runtime error (2) : out of memory at /pytorch/torch/lib/THC/generic/THCStorage.cu:58

  #24 opened 6 years ago by BruceLee0718
  3

• RuntimeError: invalid argument 2: Input tensor must have same size as output tensor apart from the specified dimension at /opt/conda/conda-

  #8 opened 6 years ago by KevinQian97
  2

• Seems like a big problem

  #35 opened 6 years ago by SunAnLan
  1

• about proposal_target_layer

  #30 opened 6 years ago by foralliance
  1

• None

  #34 opened 6 years ago by SunAnLan
  0

• here is a bug. it should not be sum_fg[i] but min(num_fg, sum_fg[i])

  #33 opened 6 years ago by SunAnLan
  0

• about proposal_target_layer

  #31 opened 6 years ago by foralliance
  0

• Incorporating Mutli-scale training and testing

  #26 opened 6 years ago by Karthik-Suresh93
  0

• how to train res101_fpn_cascade rcnn?

  #25 opened 6 years ago by guanbin1994
  0

• sh make.sh error

  #28 opened 6 years ago by he010103
  2

• My image size is 768x768, what I need to set in config?

  #17 opened 6 years ago by Bonsen
  0

• RSNA数据集

  #15 opened 6 years ago by 0xTechSavvy
  2

• roi_align bug in fpn.py

  #14 opened 6 years ago by 0xTechSavvy
  3

• from model.faster_rcnn.faster_rcnn_cascade import _fasterRCNN

  #11 opened 6 years ago by sheldon606
  2

• How to predict the image

  #9 opened 6 years ago by yuyijie1995
  2

• bbox regression normalization

  #32 opened 6 years ago by foralliance
  0

• voc_2007_test_gt_roidb.pkl is empty and pickle got EOFError

  #29 opened 6 years ago by SunAnLan
  1

• Runtime Error

  #27 opened 6 years ago by Karthik-Suresh93
  0

• While copying the parameter named RCNN_top.0.weight, whose dimensions in the model are torch.Size([1024, 256, 7, 7]) and whose dimensions in the checkpoint are torch.Size([1024, 256, 14, 14]).

  #23 opened 6 years ago by lymoon3129
  0

• The result of cascade detnet59 ?

  #20 opened 6 years ago by yanxp
  0

• where is val loss?

  #18 opened 6 years ago by Bonsen
  0

• If vis ==True in test_net.py , it shows errors.

  #19 opened 6 years ago by Bonsen
  0

• IndexError: list index out of range

  #16 opened 6 years ago by Bonsen
  0

• problems with loading detnet59.pth

  #13 opened 6 years ago by KorovkoAlexander
  1

• This project doesn't support Pytorch 0.4.0 +,

  #12 opened 6 years ago by sheldon606
  1

• RuntimeError: reciprocal is not implemented for type torch.cuda.LongTensor

  #7 opened 6 years ago by huiyang865
  1

• How to use multi-GPUs?

  #5 opened 6 years ago by Allenwutao
  3

• numpy edition problem

  #3 opened 6 years ago by yuyijie1995
  3

• is the dim of rois wrong?

  #6 opened 6 years ago
  1