FoveaBox
FoveaBox copied to clipboard
taokong
FoveaBox: Beyond Anchor-based Object Detector
CUDA:11.1 MMDET: 2.17 (open-mmlab) fsr@ServerE1:~/code/FoveaBox$ python tools/train.py "/home/fsr/code/FoveaBox/configs/foveabox/fovea_r50_fpn_4gpu_2x_align.py" 2021-09-29 19:19:16,717 - mmdet - INFO - Distributed training: False /home/laocheng/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/mmdet/models/builder.py:53: UserWarning: train_cfg and test_cfg is deprecated, please specify them in model...
1. In the result display in readme, What does "ms-train" mean? 2. Does single card training, double card training and 4GPU training have an impact on the result accuracy?
(open-mmlab) fsr@serverA2:~/FoveaBox$ python demo/webcam_demo.py configs/foveabox/fovea_r50_fpn_4gpu_2x.py checkpoints/fovea_r50_fpn_4x4_2x_coco_20200203-2df792b1.pth [ WARN:0] global /tmp/pip-req-build-cg56sov1/opencv/modules/videoio/src/cap_v4l.cpp (893) open VIDEOIO(V4L2:/dev/video0): can't open camera by index Press "Esc", "q" or "Q" to exit. Traceback (most recent call last):...
I can't download the trained model from google driver. Can you share the model on baiduyun?
hello, do you have any plans to share resnext-101 model? also I was wondering, what is the difference between your shared resnet-101 model and the one in the paper, since...
I add a mobilenet.py as GETTING_STARTED.md said , and modify the config ,but I can't run the training, how can I train the foveabox with mobilenet,please ?
