Open sycophant-stone opened 3 years ago
From the log attached(https://drive.google.com/drive/folders/1wR48k8h8mCryMw4NrfkBtocw_TGp2S1q?usp=sharing), there seems to be a pretrained model, as below shows. My concern is what mv_epoch_8.pt is and is it fair for the benchmark.
https://drive.google.com/drive/folders/1wR48k8h8mCryMw4NrfkBtocw_TGp2S1q?usp=sharing
mv_epoch_8.pt
INFO 2020-12-04 15:43:22 train.py: 178] Namespace(backbone_conf_file='../backbone_conf.yaml', backbone_type='EfficientNet', \ batch_size=512, data_root='/home/wangjun492/wj_data/faceX-Zoo/deepglint/msra_crop', epoches=18, \ head_conf_file='../head_conf.yaml', head_type='MV-Softmax', log_dir='log', lr=0.1, milestones=[10, 13, 16], momentum=0.9, \ out_dir='out_dir', pretrain_model='mv_epoch_8.pt', print_freq=200, resume=False, save_freq=3000, step='10, 13, 16', \ tensorboardx_logdir='mv-effi', train_file='/home/wangjun492/wj_data/faceX-Zoo/deepglint/msceleb_deepglint_train_file.txt', \ writer=<tensorboardX.writer.SummaryWriter object at 0x7f9ae71fce80>)
thanks, again.
in train.py line 162: conf.add_argument('--resume', '-r', action = 'store_true', default = False, help = 'Whether to resume from a checkpoint.')
resume = False means that we don't load any pretrained models.
From the log attached(
https://drive.google.com/drive/folders/1wR48k8h8mCryMw4NrfkBtocw_TGp2S1q?usp=sharing
), there seems to be a pretrained model, as below shows. My concern is whatmv_epoch_8.pt
is and is it fair for the benchmark.thanks, again.