2020-12-24 00:44:54.475679: I tensorflow/python/profiler/internal/profiler_wrapper.cc:87] Creating directory: logs/2020-12-24/train/plugins/profile/2020_12_24_00_44_54Dumped tool data for overview_page.pb to logs/2020-12-24/train/plugins/profile/2020_12_24_00_44_54/Hugode-MBP.overview_page.pb
Dumped tool data for input_pipeline.pb to logs/2020-12-24/train/plugins/profile/2020_12_24_00_44_54/Hugode-MBP.input_pipeline.pb
Dumped tool data for tensorflow_stats.pb to logs/2020-12-24/train/plugins/profile/2020_12_24_00_44_54/Hugode-MBP.tensorflow_stats.pb
Dumped tool data for kernel_stats.pb to logs/2020-12-24/train/plugins/profile/2020_12_24_00_44_54/Hugode-MBP.kernel_stats.pb
The training program can't go to Epoch (2/2), only keep at Epoch (1/2). My command is :
python3 train.py --no-snapshots --phi 0 --gpu 0 --random-transform --compute-val-loss --freeze-backbone --batch-size 32 --steps 4 pascal /Users/hugo/Downloads/VOCdevkit_2012_train/VOC2012
Could you help me how to fix it?
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.
Hugode-MBP:EfficientDet hugo$ python3 train.py --no-snapshots --phi 0 --gpu 0 --random-transform --compute-val-loss --freeze-backbone --batch-size 32 --steps 4 pascal /Users/hugo/Downloads/VOCdevkit_2012_train/VOC2012 {'dataset_type': 'pascal', 'detect_quadrangle': False, 'detect_text': False, 'snapshot': None, 'freeze_backbone': True, 'freeze_bn': False, 'weighted_bifpn': False, 'batch_size': 32, 'phi': 0, 'gpu': '0', 'epochs': 10, 'steps': 4, 'snapshot_path': 'checkpoints/2020-12-24', 'tensorboard_dir': 'logs/2020-12-24', 'snapshots': False, 'evaluation': True, 'random_transform': True, 'compute_val_loss': True, 'multiprocessing': False, 'workers': 1, 'max_queue_size': 10, 'pascal_path': '/Users/hugo/Downloads/VOCdevkit_2012_train/VOC2012'}
2020-12-24 00:44:54.475679: I tensorflow/python/profiler/internal/profiler_wrapper.cc:87] Creating directory: logs/2020-12-24/train/plugins/profile/2020_12_24_00_44_54Dumped tool data for overview_page.pb to logs/2020-12-24/train/plugins/profile/2020_12_24_00_44_54/Hugode-MBP.overview_page.pb Dumped tool data for input_pipeline.pb to logs/2020-12-24/train/plugins/profile/2020_12_24_00_44_54/Hugode-MBP.input_pipeline.pb Dumped tool data for tensorflow_stats.pb to logs/2020-12-24/train/plugins/profile/2020_12_24_00_44_54/Hugode-MBP.tensorflow_stats.pb Dumped tool data for kernel_stats.pb to logs/2020-12-24/train/plugins/profile/2020_12_24_00_44_54/Hugode-MBP.kernel_stats.pb
4/4 [==============================] - ETA: 0s - loss: 1.7616 - classification_loss: 1.2421 - regression_loss: 0.5194
======================================================================================
The training program can't go to Epoch (2/2), only keep at Epoch (1/2). My command is : python3 train.py --no-snapshots --phi 0 --gpu 0 --random-transform --compute-val-loss --freeze-backbone --batch-size 32 --steps 4 pascal /Users/hugo/Downloads/VOCdevkit_2012_train/VOC2012 Could you help me how to fix it?