|
- =====> Configuration
- Namespace(cuda=True, epoch=25, lr=0.0001, batch_size=1, pre_batch_size=4, sample_number=3, sam_number=5, mode='pre_train', model_name='alpha1', num_repeats=100, num_classes=1, random_seed=20230930, size=224, video_list_dir='/home/wislab/bryan/VSOD/tools', restore_from=None, sample_gap=5, test_batch_size=1, num_thread=0, model_path='', weights_save_fold='./outputs/weights', log_save_fold='./outputs/logs/', input_size=512, test_dataset=['ViSal', 'DAVSOD', 'FBMS', 'SegV2'], testsavefold='./prediction', ds_name='DAVSOD')
- =====> Configuration
- Namespace(cuda=True, epoch=25, lr=0.0001, batch_size=1, pre_batch_size=4, sample_number=3, sam_number=5, mode='pre_train', model_name='alpha1', num_repeats=100, num_classes=1, random_seed=20230930, size=224, video_list_dir='/home/wislab/bryan/VSOD/tools', restore_from=None, sample_gap=5, test_batch_size=1, num_thread=0, model_path='', weights_save_fold='./outputs/weights', log_save_fold='./outputs/logs/', input_size=512, test_dataset=['ViSal', 'DAVSOD', 'FBMS', 'SegV2'], testsavefold='./prediction', ds_name='DAVSOD')
- =====> Set GPU for training
- =====> Building network
- single GPU for training
- =====> Computing network parameters
- Total network parameters: 84684273
- =====> Begin to train
- start_time: 1696130601.246688
- ---> epoch: 0
- =====> Configuration
- Namespace(cuda=True, epoch=25, lr=0.0001, batch_size=1, pre_batch_size=4, sample_number=3, sam_number=5, mode='pre_train', model_name='alpha1', num_repeats=100, num_classes=1, random_seed=20230930, size=224, video_list_dir='/home/wislab/bryan/VSOD/tools', restore_from=None, sample_gap=5, test_batch_size=1, num_thread=0, model_path='', weights_save_fold='./outputs/weights', log_save_fold='./outputs/logs/', input_size=512, test_dataset=['ViSal', 'DAVSOD', 'FBMS', 'SegV2'], testsavefold='./prediction', ds_name='DAVSOD')
- =====> Set GPU for training
- =====> Random Seed: 20230930
- =====> Building network
- single GPU for training
- =====> Computing network parameters
- Total network parameters: 84684273
- =====> Begin to train
- iteration numbers of per epoch: 2638
- epoch num: 25
- start_time: 1696130736.206367
- ---> epoch: 0
- =====> Configuration
- Namespace(cuda=True, epoch=25, lr=0.0001, batch_size=1, pre_batch_size=4, sample_number=3, sam_number=5, mode='pre_train', model_name='alpha1', num_repeats=100, num_classes=1, random_seed=20230930, size=224, video_list_dir='/home/wislab/bryan/VSOD/tools', restore_from=None, sample_gap=5, test_batch_size=1, num_thread=0, model_path='', weights_save_fold='./outputs/weights', log_save_fold='./outputs/logs/', input_size=512, test_dataset=['ViSal', 'DAVSOD', 'FBMS', 'SegV2'], testsavefold='./prediction', ds_name='DAVSOD')
- =====> Set GPU for training
- =====> Random Seed: 20230930
- =====> Building network
- single GPU for training
- =====> Computing network parameters
- Total network parameters: 84684273
- =====> Begin to train
- iteration numbers of per epoch: 2638
- epoch num: 25
- start_time: 1696131288.5553324
- ---> epoch: 0
- =====> Configuration
- Namespace(cuda=True, epoch=25, lr=0.0001, batch_size=1, pre_batch_size=4, sample_number=3, sam_number=5, mode='pre_train', model_name='alpha1', num_repeats=100, num_classes=1, random_seed=20230930, size=224, video_list_dir='/home/wislab/bryan/VSOD/tools', restore_from=None, sample_gap=5, test_batch_size=1, num_thread=0, model_path='', weights_save_fold='./outputs/weights', log_save_fold='./outputs/logs/', input_size=512, test_dataset=['ViSal', 'DAVSOD', 'FBMS', 'SegV2'], testsavefold='./prediction', ds_name='DAVSOD')
- =====> Set GPU for training
- =====> Random Seed: 20230930
- =====> Building network
- single GPU for training
- =====> Computing network parameters
- Total network parameters: 84684273
- =====> Begin to train
- iteration numbers of per epoch: 2638
- epoch num: 25
- start_time: 1696131634.2617812
- ---> epoch: 0
- =====> Configuration
- Namespace(cuda=True, epoch=25, lr=0.0001, batch_size=1, pre_batch_size=4, sample_number=3, sam_number=6, mode='pre_train', model_name='alpha1', num_repeats=100, num_classes=1, random_seed=20230930, size=224, video_list_dir='/home/wislab/bryan/VSOD/tools', restore_from=None, sample_gap=5, test_batch_size=1, num_thread=0, model_path='', weights_save_fold='./outputs/weights', log_save_fold='./outputs/logs/', input_size=512, test_dataset=['ViSal', 'DAVSOD', 'FBMS', 'SegV2'], testsavefold='./prediction', ds_name='DAVSOD')
- =====> Set GPU for training
- =====> Random Seed: 20230930
- =====> Building network
- single GPU for training
- =====> Computing network parameters
- Total network parameters: 85274106
- =====> Begin to train
- iteration numbers of per epoch: 2638
- epoch num: 25
- start_time: 1696131702.422337
- ---> epoch: 0
- =====> Configuration
- Namespace(cuda=True, epoch=25, lr=0.0001, batch_size=1, pre_batch_size=4, sample_number=3, sam_number=6, mode='pre_train', model_name='alpha1', num_repeats=100, num_classes=1, random_seed=20230930, size=224, video_list_dir='/home/wislab/bryan/VSOD/tools', restore_from=None, sample_gap=5, test_batch_size=1, num_thread=0, model_path='', weights_save_fold='./outputs/weights', log_save_fold='./outputs/logs/', input_size=512, test_dataset=['ViSal', 'DAVSOD', 'FBMS', 'SegV2'], testsavefold='./prediction', ds_name='DAVSOD')
- =====> Set GPU for training
- =====> Random Seed: 20230930
- =====> Building network
- single GPU for training
- =====> Computing network parameters
- Total network parameters: 85274106
- =====> Begin to train
- iteration numbers of per epoch: 2638
- epoch num: 25
- start_time: 1696131873.5598981
- ---> epoch: 0
- =====> Configuration
- Namespace(cuda=True, epoch=25, lr=0.0001, batch_size=1, pre_batch_size=6, sample_number=3, sam_number=6, mode='pre_train', model_name='alpha1', num_repeats=100, num_classes=1, random_seed=20230930, size=224, video_list_dir='/home/wislab/bryan/VSOD/tools', restore_from=None, sample_gap=5, test_batch_size=1, num_thread=0, model_path='', weights_save_fold='./outputs/weights', log_save_fold='./outputs/logs/', input_size=512, test_dataset=['ViSal', 'DAVSOD', 'FBMS', 'SegV2'], testsavefold='./prediction', ds_name='DAVSOD')
- =====> Set GPU for training
- =====> Random Seed: 20230930
- =====> Building network
- single GPU for training
- =====> Computing network parameters
- Total network parameters: 85274106
- =====> Begin to train
- iteration numbers of per epoch: 1758
- epoch num: 25
- start_time: 1696131948.8812225
- ---> epoch: 0
- =====> Configuration
- Namespace(cuda=True, epoch=25, lr=0.0001, batch_size=1, pre_batch_size=6, sample_number=3, sam_number=5, mode='pre_train', model_name='alpha1', num_repeats=100, num_classes=1, random_seed=20230930, size=224, video_list_dir='/home/wislab/bryan/VSOD/tools', restore_from=None, sample_gap=5, test_batch_size=1, num_thread=0, model_path='', weights_save_fold='./outputs/weights', log_save_fold='./outputs/logs/', input_size=512, test_dataset=['ViSal', 'DAVSOD', 'FBMS', 'SegV2'], testsavefold='./prediction', ds_name='DAVSOD')
- =====> Set GPU for training
- =====> Random Seed: 20230930
- =====> Building network
- single GPU for training
- =====> Computing network parameters
- Total network parameters: 84684273
- =====> Begin to train
- iteration numbers of per epoch: 1758
- epoch num: 25
- start_time: 1696131962.958098
- ---> epoch: 0
- # train_loss: 2810.577456
- =====> saving model
- ---> epoch: 1
- # train_loss: 2651.902045
- =====> saving model
- ---> epoch: 2
- # train_loss: 2498.342678
- =====> saving model
- ---> epoch: 3
- # train_loss: 2360.807809
- =====> saving model
- ---> epoch: 4
- # train_loss: 2215.877464
- =====> saving model
- ---> epoch: 5
- # train_loss: 2078.790376
- =====> saving model
- ---> epoch: 6
- # train_loss: 1949.076723
- =====> saving model
- ---> epoch: 7
- # train_loss: 1825.046850
- =====> saving model
- ---> epoch: 8
- # train_loss: 1709.300597
- =====> saving model
- ---> epoch: 9
- # train_loss: 1598.449772
- =====> saving model
- ---> epoch: 10
- # train_loss: 1488.924831
- =====> saving model
- ---> epoch: 11
- # train_loss: 1391.687414
- =====> saving model
- ---> epoch: 12
- # train_loss: 1309.321279
- =====> saving model
- ---> epoch: 13
- # train_loss: 1432.214951
- =====> saving model
- ---> epoch: 14
- # train_loss: 1238.494176
- =====> saving model
- ---> epoch: 15
- # train_loss: 1112.230451
- =====> saving model
- ---> epoch: 16
- # train_loss: 1079.268022
- =====> saving model
- ---> epoch: 17
- # train_loss: 1014.675708
- =====> saving model
- ---> epoch: 18
- # train_loss: 918.028895
- =====> saving model
- ---> epoch: 19
- # train_loss: 853.808400
- =====> saving model
- ---> epoch: 20
- # train_loss: 864.715774
- =====> saving model
- ---> epoch: 21
- # train_loss: 808.547811
- =====> saving model
- ---> epoch: 22
- # train_loss: 699.517229
- =====> saving model
- ---> epoch: 23
- # train_loss: 663.000197
- =====> saving model
- ---> epoch: 24
- # train_loss: 603.780255
- =====> saving model
|