facebookresearch / maskrcnn-benchmark

Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.

facebookresearch/maskrcnn-benchmark Issues

Does the optimized branch support Multinode implementation
Updated 8 months ago
5 | #include <THC/THC.h> | ^~~~~~~~~~~ compilation terminated. error: command '/usr/local/cuda/bin/nvcc' failed with exit code 1
Closed 2 years ago8
Why the validation loss is always increasing?
Updated a year ago
RuntimeError: cuda runtime error (48) : no kernel image is available for execution on the device at /maskrcnn_benchmark/csrc/cuda/ROIAlign_cuda.cu:297
Closed 3 years ago5
Kabjhah
Updated a year ago
errors in python setup.py in windows11
Updated a year ago
Is it necessary to delete these parameters to fine-tune model when the number of classes changed?
Updated a year ago
ModuleNotFoundError: No module named 'cityscapesscripts'
Updated a year ago
Mask Rcnn is too slow in Google Colab
Closed a year ago
THCudaCheck FAIL invalid device function
Updated a year ago
ImportError: cannot import name '_C' from 'maskrcnn_benchmark'
Updated a year ago2
error: option --cuda_ext not recognized
Closed a year ago1
Program card in the first epoch is unable to start training
Updated a year ago1
lr=0.0025 for single GPU training still cause nan in few iteration
Updated a year ago
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
Updated a year ago1
if torch._six.PY3: AttributeError: module 'torch._six' has no attribute 'PY3'
Closed 2 years ago3
## ❓ Questions and Help AttributeError：NMS
Updated 2 years ago
AttributeError:NMS
Closed 2 years ago
AttributeError: module ‘torch.cuda’ has no attribute ‘amp’
Updated 2 years ago5
Will you release this with newest version of pytorch?
Updated 2 years ago
Can this project work with CUDA 11 and Pytorch 1.9.0?
Updated 2 years ago5
PASCAL VOC with ResNet 152 - mask is not shown
Updated 2 years ago
ModuleNotFoundError: No module named 'yacs'
Updated 2 years ago1
AttributeError: 'list' object has no attribute 'numel'
Updated 2 years ago1
ImportError: DLL load failed while importing _C
Updated 2 years ago1
training job failed
Closed 2 years ago1
AttributeError: 'tuple' object has no attribute 'values'
Updated 2 years ago
Not sure about the difference between two models
Updated 2 years ago
Not compiled with GPU support
Updated 2 years ago
when i use this to generate scene graph,i get "RuntimeError"
Updated 2 years ago
when i run webcam.py ，ModuleNotFoundError: No module named 'maskrcnn_benchmark'
Updated 2 years ago
training loss hovering around few values
Updated 2 years ago
ModuleNotFoundError: No module named 'fast_layer_norm'
Updated 2 years ago
Segmentation fault (core dumped)
Updated 2 years ago
How to Use Images Instead of Proposals in ROI_Head Predictors?
Updated 2 years ago
3080 train
Updated 2 years ago
_C.SOLVER.TEST_PERIOD
Updated 3 years ago
plot realtime by python
Updated 3 years ago
while running the fwg command i m getting this error .please help
Updated 3 years ago
cannot import name 'COCODemo' from 'predictor'
Updated 3 years ago
I need only bbox of my own datasets by using model. Simple way please~
Updated 3 years ago
How to install pytorch-nightly 1.0 ?
Closed 3 years ago3
only one GPU, I met the error that "Default process group is not initialized"
Updated 3 years ago
How to extract undetected object class labels after extracting `y_pred` from `predictions.pth` inference file.
Updated 3 years ago
ImportError: cannot import name '_C' from 'maskrcnn_benchmark'
Updated 3 years ago1
How can i get .pkl file conataing bounding boxes with class_id and scores ?
Updated 3 years ago
Image type of COCODataset class
Closed 3 years ago1
cannot evalute
Updated 3 years ago
ninja compile on win10,cuda10.1
Updated 3 years ago
Installation fails with recent PyTorch releases
Updated 3 years ago