代码拉取完成,页面将自动刷新
Method | COCO | VOC2007 |
---|---|---|
ML-GCN | 83.0 | 94.0 |
Ours(Mix-GCN+PPIR) | 84.3 | 95.6 |
Please, install the following packages
python3 download.py
checkpoint/coco (Dropbox)
checkpoint/voc (Dropbox)
lr
: learning ratelrp
: factor for learning rate of pretrained layers. The learning rate of the pretrained layers is lr * lrp
batch-size
: number of images per batchimage-size
: size of the imageepochs
: number of training epochsevaluate
: evaluate model on validation setresume
: path to checkpointCUDA_VISIBLE_DEVICES=1 python3 demo_voc2007_gcn.py data/voc --image-size 448 --batch-size 32 -e --resume checkpoint/voc/voc_checkpoint.pth.tar
CUDA_VISIBLE_DEVICES=1 python3 demo_coco_gcn.py data/coco/ --image-size 448 --batch-size 32 -e --resume checkpoint/coco/coco_checkpoint.pth.tar
This project is based on https://github.com/durandtibo/wildcat.pytorch
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。