easy-faster-rcnn.pytorch
easy-faster-rcnn.pytorch copied to clipboard
potterhsu
An easy implementation of Faster R-CNN (https://arxiv.org/pdf/1506.01497.pdf) in PyTorch.
  number_class is wrong! coco2017 is actually not 92.
For the WarmUpMultiStepLR, if we maintain the default factor and warm up steps, the learning rate will tend to be 0 after several steps since the lr is mulplicated by...
Hi,author When I compile the program with code: python test/nms/test_nms.py I met a error: ImportError: /home/liushuai/STUDY/MyWorkSpace/object_detection_test/easy-faster-rcnn.pytorch-master/support/_C.cpython-36m-x86_64-linux-gnu.so: undefined symbol: _ZN3c105ErrorC1ENS_14SourceLocationERKSs How can I solve it? I hope you can give me...
Hi, potterhsu, Thank you very much for your code, I run it well but I have a question here about the detach of proposal boxes, why it should be detached,...
Hi, Is this repository allow considering negative images as well for training? For example, while training a cat detector, one may have some images containing cats (+ve images) and some...
This pull request adds the support to train a person detector using only person images of VOC2007 dataset. One can pass `-s=voc2007-person` argument to `train.py` to train a peson detector...
C:\WinPython\WPy64-3741\easy-faster-rcnn.pytorch-master\easy-faster-rcnn.pytorch-master>python support/setup.py develop running develop running egg_info writing support.egg-info\PKG-INFO writing dependency_links to support.egg-info\dependency_links.txt writing top-level names to support.egg-info\top_level.txt reading manifest file 'support.egg-info\SOURCES.txt' writing manifest file 'support.egg-info\SOURCES.txt' running build_ext C:\WinPython\WPy64-3741\python-3.7.4.amd64\lib\site-packages\torch\utils\cpp_extension.py:209: UserWarning:...
hi @potterhsu iam trying to train using faster R-CNN model on my custom dataset. Basically my custom data just include 2 classes, and the data had labelled too, based on...
Hi, thanks for nice implementation. I was struggling for a while to make it run until it became clear to me that even the inference won't run without CUDA (see...
