faster-rcnn.pytorch
faster-rcnn.pytorch copied to clipboard
jwyang
A faster pytorch implementation of faster r-cnn
Thank you for this code, it's amazing! I've been learning about your project recently, but this error occurred at the beginning of the training. I thought the graphics card didn't...
Hi, I'm trying to use the code to train my data, but it can not work Sometimes in the first print_log, loss is not nan: [session 1][epoch 1][iter 0/ 300]...
In the cfgs folder, what is the difference between RPN_BATCHSIZE, BATCH_SIZE in res101.yml and batch_size in trainval_net.py? Can I set the BATCH_SIZE of res101.yml to 1, and what are the...
The processing of compiling is successful, without errors but a warning: **command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++** Then, when I try **train_val.py**, errors occured:...
gcc -pthread -shared -std=c99 ./_nms.o ./home/ssd1/test/faster-rcnn.pytorch/lib/model/nms/src/nms_cuda.o /home/ssd1/test/faster-rcnn.pytorch/lib/model/nms/src/nms_cuda_kernel.cu.o -L/home/work/python/build/lib -lpython2.7 -o ./_nms.so /usr/bin/ld: cannot find -lpython2.7 collect2: ld returned 1 exit status Traceback (most recent call last): File "build.py", line 37,...
I use Tesla T4, and add the CUDA_ARCH: -gencode arch=compute_75,code=sm_75 but when I run make.sh I get this error: nvcc fatal : Unsupported gpu architecture 'compute_75' How do I fix...
my data is jpg-8bit from .dicom,they are gray image. i want to add cv2.equalizeHist, but i do not know which .py and which line can apply this code. anybody konw...
When I attempt to train, the problem occured: `Traceback (most recent call last): File "trainval_net.py", line 30, in from model.utils.net_utils import weights_normal_init, save_net, load_net, \ File "/root/workspace/object-detection/faster-rcnn.pytorch/lib/model/utils/net_utils.py", line 8, in...
Is there a vgg16 based model for coco dataset? Although there list results of vgg16 based model, there's no link to download the model. Anybody can provide a model? Many...
in the bbox_transform when we compute overlap i have problems understanding the steps :( what is ` iw = (torch.min(boxes[:,:,:,2], query_boxes[:,:,:,2]) - torch.max(boxes[:,:,:,0], query_boxes[:,:,:,0]) + 1)` ` iw[iw < 0]...
