FCOS
FCOS copied to clipboard
FCOS: Fully Convolutional One-Stage Object Detection (ICCV'19)
running build running build_py running egg_info writing fcos.egg-info/PKG-INFO writing dependency_links to fcos.egg-info/dependency_links.txt writing requirements to fcos.egg-info/requires.txt writing top-level names to fcos.egg-info/top_level.txt reading manifest file 'fcos.egg-info/SOURCES.txt' reading manifest template 'MANIFEST.in' writing...
(t != class_range) * (t >= 0) is always return a tensor which all values is True, I think it is a bug in cpu version
How to perform cross-validation during distributed training? Thank you so much.
I am very confused why can't we set the negative label of centerness as 0. And train centerness in all positive and negative sample. I'm looking forward to the reply....
When I run the command: nvidia-docker build -t maskrcnn-benchmark --build-arg CUDA=10.0 --build-arg CUDNN=7 docker/ the following problem occurs:/bin/sh: 1: /miniconda/bin/conda: not found but “Dockerfile ” shows that minionda is installed...
Hello, Do you plan to integrate the HRNet backbone into your improvement FCOS version? It seems like your HRNet version is on the original FCOS version, the HRNet backbone may...
transform = T.Compose( [ T.Resize(min_size, max_size), T.RandomHorizontalFlip(flip_prob), T.ToTensor(), normalize_transform, ] there are only aumentations like image resize, rotate etc i want to add some augmentations about image color, how to...
Traceback (most recent call last): File "tools/train_net.py", line 180, in main() File "tools/train_net.py", line 173, in main model = train(cfg, args.local_rank, args.distributed) File "tools/train_net.py", line 79, in train arguments, File...
FileNotFoundError: [Errno 2] No such file or directory: 'FCOS_imprv_R_50_FPN_1x.pth'