代码拉取完成,页面将自动刷新
同步操作将从 金色木叶枫/PaddleVideo 强制同步,此操作会覆盖自 Fork 仓库以来所做的任何修改,且无法恢复!!!
确定后同步将在后台操作,完成时将刷新页面,请耐心等待。
export CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
# run tsm training
#python3.7 -B -m paddle.distributed.launch --gpus="0,1,2,3" --log_dir=log_tsm main.py --validate -c configs/recognition/tsm/tsm.yaml -o log_level="INFO" -o DATASET.batch_size=16
# run tsn training
#python3.7 -B -m paddle.distributed.launch --gpus="0,1,2,3" --log_dir=log_tsn main.py --validate -c configs/recognition/tsn/tsn.yaml -o log_level="INFO"
# run slowfast training
#python3.7 -B -m paddle.distributed.launch --gpus="0,1,2,3,4,5,6,7" --log_dir=log_slowfast main.py --validate -c configs/recognition/slowfast/slowfast.yaml -o log_level="INFO"
# run bmn training
#python3.7 -B -m paddle.distributed.launch --gpus="0,1,2,3" --log_dir=log_bmn main.py --validate -c configs/localization/bmn.yaml
# run attention_lstm training
#python3.7 -B -m paddle.distributed.launch --gpus="0,1,2,3,4,5,6,7" --log_dir=log_attetion_lstm main.py --validate -c configs/recognition/attention_lstm/attention_lstm.yaml -o log_level="INFO"
# run pp-tsm training
python3.7 -B -m paddle.distributed.launch --gpus="0,1,2,3" --log_dir=log_pptsm main.py --validate -c configs/recognition/tsm/pptsm.yaml -o log_level="INFO"
# run tsn dali training
#python3.7 -B -m paddle.distributed.launch --gpus="0,1,2,3" --log_dir=log_tsn main.py --train_dali -c configs/recognition/tsn/tsn_dali.yaml -o log_level="INFO"
# test.sh
# just use `example` as example, please replace to real name.
#python3.7 -B -m paddle.distributed.launch --gpus="0,1,2,3,4,5,6,7" --log_dir=log_test main.py --test -c configs/example.yaml -w "output/example/example_best.pdparams"
#NOTE: run bmn test, only support single card, bs=1
#python3.7 main.py --test -c configs/localization/bmn.yaml -w output/BMN/BMN_epoch_00010.pdparams -o DATASET.batch_size=1
# export_models script
# just use `example` as example, please replace to real name.
#python3.7 tools/export_model.py -c configs/example.yaml -p output/example/example_best.pdparams -o ./inference
# predict script
# just use `example` as example, please replace to real name.
#python3.7 tools/predict.py -v example.avi --model_file "./inference/example.pdmodel" --params_file "./inference/example.pdiparams" --enable_benchmark=False --model="example" --num_seg=8
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。