ijkguo/mx-rcnn

Issues

• cannot reproduce faster rcnn mAP

  #72 opened 7 years ago by jiangxiaoyan
  10

• Custom Training: Training on custom dataset

  #36 opened 8 years ago by dubur
  2

• AttributeError: 'module' object has no attribute 'Proposal'

  #45 opened 8 years ago by iFighting
  21

• Custom Training: RuntimeWarning: invalid value encountered in greater_equal

  #29 opened 8 years ago by longwoo
  9

• why slower than py-faster-rcnn ?

  #67 opened 6 years ago by OMG59E
  6

• Issues with pretrained models

  #71 opened 6 years ago by AleBasso80
  1

• Trained resnet is good performance ,but run the demo.py it si bad.

  #60 opened 7 years ago by abner2015
  6

• approximate joint end-2-end training.

  #23 opened 8 years ago by tornadomeet
  26

• Implementation differences compared to Caffe

  #59 opened 8 years ago by nirbenz
  7

• time comsumed for inference

  #62 opened 7 years ago by JacobWang95
  2

• CPU only mode fail to install cython extension

  #68 opened 7 years ago by younseunghyun
  2

• Is this a bug in computing Anchors?

  #70 opened 7 years ago by dongxiao92
  2

• support of more than one image per gpu

  #69 opened 7 years ago by xiazhu
  1

• lr policy for COCO

  #65 opened 7 years ago by DengpanFu
  3

• network.resnet.FIXED_PARAMS_SHARED in config.py

  #66 opened 7 years ago by weiliuxm
  1

• multi-gpu problem

  #63 opened 8 years ago by niluanwudidadi
  2

• a question about cudnn autotune

  #64 opened 8 years ago by niluanwudidadi
  2

• trained model with ResNet-101

  #53 opened 8 years ago by wzkg2012
  3

• KeyError: 'width'

  #58 opened 8 years ago by Fansiee
  10

• Difference between CXX_PROPOSAL and custom proposal?

  #61 opened 8 years ago by xinghedyc
  2

• Error in downloading pre-trained model

  #47 opened 8 years ago by dakshvar22
  10

• RuntimeError: rpn_bbox_pred_bias is not presented

  #48 opened 8 years ago by dakshvar22
  8

• Custom Training: Infer_shape error when training rcnn

  #40 opened 8 years ago
  7

• data label empty error

  #46 opened 8 years ago by atticcas
  1

• What's next?

  #44 opened 8 years ago by ijkguo
  1

• How to resume training with a specific epoch when running train_end2end.py?

  #57 opened 8 years ago by breeze5428
  4

• AssertionError: Single batch only_

  #55 opened 8 years ago by weiliuxm
  4

• IndexError: list index out of range

  #54 opened 8 years ago by breeze5428
  2

• How can I train the data without the pretrained model ?

  #52 opened 8 years ago by mu001999
  4

• No module named bbox when running train_end2end.py

  #51 opened 8 years ago by mu001999
  1

• training error with latest version (1/20/17)

  #50 opened 8 years ago by jwnsu
  3

• MEM/HANG: rcnn demo.py error

  #38 opened 8 years ago by niluanwudidadi
  3

• MEM/HANG: cuda out of memory

  #35 opened 8 years ago by nankezi
  17

• Check failed: param_.op_type != "" ( vs. ) Custom operator type missing

  #49 opened 8 years ago by weiliuxm
  12

• demo.py error: decide_slices assert len(data_shapes) > 0

  #43 opened 8 years ago by nankezi
  4

• ResNet: overflow problem in bbox

  #30 opened 8 years ago by longwoo
  3

• ResNet: Problem when using Resnet as base net

  #31 opened 8 years ago
  3

• final-0000.params

  #41 opened 8 years ago by Walid-Ahmed
  1

• training with multiple gpu?

  #42 opened 8 years ago by hengck23
  2

• final-0000.params

  #26 opened 8 years ago by Aspirinkb
  2

• Error when train end2end

  #34 opened 8 years ago by OnlySang
  15

• problem python train_alternate.py --gpus 0.

  #32 opened 8 years ago by darrylbobo
  3

• question in fix_param

  #39 opened 8 years ago by li-haoran
  0

• Hi, When I run demo.py on CPU, there is a error: mxnet.base.MXNetError: [00:42:42] src/operator/./convolution-inl.h:299: Check failed: (param_.workspace) >= (required_size) Minimum workspace size: 1228800000 Bytes Given: 1073741824 Byteequired_size) Minimum workspace size: 1228800000 Bytes Given: 1073741824 Bytes

  #37 opened 8 years ago by alysazhang
  2

• Check failed: (param_.workspace) >= (required_size)

  #28 opened 8 years ago by zhyj3038
  3

• Is the result of demo right?

  #33 opened 8 years ago by KeyKy
  2

• train faster rcnn

  #27 opened 8 years ago by zhyj3038
  1

• Failed to test demo.py

  #25 opened 8 years ago by wangg12
  2

• memory leak?

  #22 opened 8 years ago by zhangjiangqige
  5

• reshape in symbol of get_vgg_rcnn()

  #24 opened 8 years ago by tornadomeet
  4