facebookresearch/maskrcnn-benchmark

Issues

• Does the optimized branch support Multinode implementation

  #1358 opened a year ago by sowmya04101998
  0

• 5 | #include <THC/THC.h> | ^~~~~~~~~~~ compilation terminated. error: command '/usr/local/cuda/bin/nvcc' failed with exit code 1

  #1340 opened 2 years ago by Souryadipstan
  8

• Why the validation loss is always increasing?

  #1357 opened a year ago by imzhangyd
  0

• RuntimeError: cuda runtime error (48) : no kernel image is available for execution on the device at /maskrcnn_benchmark/csrc/cuda/ROIAlign_cuda.cu:297

  #1314 opened 3 years ago by lqniunjunlper
  5

• Kabjhah

  #1356 opened 2 years ago by kabjah
  0

• errors in python setup.py in windows11

  #1355 opened 2 years ago by xywhat
  0

• Is it necessary to delete these parameters to fine-tune model when the number of classes changed?

  #1354 opened 2 years ago by 4daJKong
  0

• ModuleNotFoundError: No module named 'cityscapesscripts'

  #1353 opened 2 years ago by Yuejingkun
  0

• Mask Rcnn is too slow in Google Colab

  #1349 opened 2 years ago by hasanhut
  0

• THCudaCheck FAIL invalid device function

  #1351 opened 2 years ago by selcukyazar
  0

• ImportError: cannot import name '_C' from 'maskrcnn_benchmark'

  #1346 opened 2 years ago by AlexanderWeismannn
  2

• error: option --cuda_ext not recognized

  #1350 opened 2 years ago by pronaykp
  1

• Program card in the first epoch is unable to start training

  #1348 opened 2 years ago by HUBUwg96
  1

• lr=0.0025 for single GPU training still cause nan in few iteration

  #1347 opened 2 years ago by suxi1111
  0

• ImportError: /home/yangyang/anaconda3/envs/pytorch_4/lib/python3.6/site-packages/syncbn_gpu-0.0.0-py3.6-linux-x86_64.egg/syncbn_gpu.cpython-36m-x86_64-linux-gnu.so: undefined symbol: _ZN3c105ErrorC1ENS_14SourceLocationERKNSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEE

  #1309 opened 4 years ago by buzhidaoshenme
  1

• if torch._six.PY3: AttributeError: module 'torch._six' has no attribute 'PY3'

  #1341 opened 2 years ago by Souryadipstan
  3

• ## ❓ Questions and Help AttributeError：NMS

  #1345 opened 2 years ago by SSSeven7
  0

• AttributeError:NMS

  #1344 opened 2 years ago by SSSeven7
  0

• AttributeError: module ‘torch.cuda’ has no attribute ‘amp’

  #1327 opened 3 years ago by suresh-s
  5

• Will you release this with newest version of pytorch?

  #1343 opened 2 years ago by PhanThanhTrung
  0

• Can this project work with CUDA 11 and Pytorch 1.9.0?

  #1322 opened 3 years ago by ghfdjsk
  5

• PASCAL VOC with ResNet 152 - mask is not shown

  #1342 opened 2 years ago by suresh-s
  0

• ModuleNotFoundError: No module named 'yacs'

  #1318 opened 3 years ago by Leo0408
  1

• AttributeError: 'list' object has no attribute 'numel'

  #1326 opened 3 years ago by gzgz-code
  1

• ImportError: DLL load failed while importing _C

  #1316 opened 3 years ago by ctxjason
  1

• training job failed

  #1329 opened 3 years ago by manibharathy1
  1

• AttributeError: 'tuple' object has no attribute 'values'

  #1339 opened 3 years ago by chenfangchenf
  0

• Not sure about the difference between two models

  #1338 opened 3 years ago by JosephJohannson
  0

• Not compiled with GPU support

  #1337 opened 3 years ago by AnaRhisT94
  0

• when i use this to generate scene graph,i get "RuntimeError"

  #1336 opened 3 years ago by xixihawokao
  0

• when i run webcam.py ，ModuleNotFoundError: No module named 'maskrcnn_benchmark'

  #1335 opened 3 years ago by yuheyuan
  0

• training loss hovering around few values

  #1334 opened 3 years ago by janmejaya-nanda
  0

• ModuleNotFoundError: No module named 'fast_layer_norm'

  #1332 opened 3 years ago by Zhefei777
  0

• Segmentation fault (core dumped)

  #1331 opened 3 years ago by Y1nFaChu
  0

• How to Use Images Instead of Proposals in ROI_Head Predictors?

  #1330 opened 3 years ago by zhanwenchen
  0

• 3080 train

  #1328 opened 3 years ago by zhouyingchaoAI
  0

• _C.SOLVER.TEST_PERIOD

  #1325 opened 3 years ago by gzgz-code
  0

• plot realtime by python

  #1324 opened 3 years ago by shamilkh007
  0

• while running the fwg command i m getting this error .please help

  #1323 opened 3 years ago by ajitrai4369
  0

• cannot import name 'COCODemo' from 'predictor'

  #1321 opened 3 years ago by tianrking
  0

• I need only bbox of my own datasets by using model. Simple way please~

  #1320 opened 3 years ago by danke1
  0

• How to install pytorch-nightly 1.0 ?

  #1317 opened 3 years ago by nanzh-19
  3

• only one GPU, I met the error that "Default process group is not initialized"

  #1319 opened 3 years ago by nanzh-19
  0

• How to extract undetected object class labels after extracting `y_pred` from `predictions.pth` inference file.

  #1315 opened 3 years ago by Eldad27
  0

• ImportError: cannot import name '_C' from 'maskrcnn_benchmark'

  #1313 opened 3 years ago by Jackson-zhao97
  1

• How can i get .pkl file conataing bounding boxes with class_id and scores ?

  #1312 opened 3 years ago by mathshangw
  0

• Image type of COCODataset class

  #1311 opened 3 years ago by leop123
  1

• cannot evalute

  #1310 opened 3 years ago by Zhefei777
  0

• ninja compile on win10,cuda10.1

  #1308 opened 4 years ago by peter5232
  0

• Installation fails with recent PyTorch releases

  #1307 opened 4 years ago by wanderingWitch
  0