faster-rcnn.pytorch
faster-rcnn.pytorch copied to clipboard
jwyang
A faster pytorch implementation of faster r-cnn
I have a custom dataset which only has only one category. And the dataset is pretty small (training around 150 images). When I tried Faster RCNN with 500 epoch. I...
Hello, I'd just like to confirm whether the ground truth bounding box format is (x,y,w,h) or (x,y, w, h)? If I'm not wrong it should be the first one correct?...
CUDA_VISIBLE_DEVICES=$GPU_ID python trainval_net.py --dataset pascal_voc --net vgg16 --bs $BATCH_SIZE --nw $WORKER_NUMBER --lr $LEARNING_RATE --lr_decay_step $DECAY_STEP --cuda Traceback (most recent call last): File "trainval_net.py", line 31, in from model.utils.net_utils import weights_normal_init,...
``` CUDA_VISIBLE_DEVICES=0 python trainval_net.py --dataset pascal_voc --net vgg16 --bs 4 --nw 4 --lr 0.01 --lr_decay_step 10 --cuda Called with args: Namespace(batch_size=4, checkepoch=1, checkpoint=0, checkpoint_interval=10000, checksession=1, class_agnostic=False, cuda=True, dataset='pascal_voc', disp_interval=100, large_scale=False,...
: unrecognized error code at /home/wangchang2/faster-rcnn.pytorch-pytorch-1.0/faster-rcnn.pytorch-pytorch-1.0/lib/model/csrc/cuda/ROIAlign_cuda.cu:297 Segmentation fault (core dumped)
Hello everyone! when I run command python setup.py build develop it raise the error: 'C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v10.0\\bin\\nvcc.exe' failed with exit status 1. How can I solve this problem...
My error is command 'C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v10.1\\bin\\nvcc.exe' failed with exit status 1
I received the error when I was running, >python setup.py build develop ``` running build running build_py running build_ext building 'model._C' extension gcc -pthread -B /cvdata/anaconda3/envs/krm2/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g...
I run test_net.py and got all 0 results. I have checked all the related issue and nothing could be done. I notice that in roibatchLoader.py, gt_boxes are make all 1...
I am confused about the line 250 in lib/model/faster_rcnn/resnet.py why we should fix some layer in ResNet? # Fix blocks for p in self.RCNN_base[0].parameters(): p.requires_grad=False for p in self.RCNN_base[1].parameters(): p.requires_grad=False...
