I changed all the paths in the 3_train.py in order for it to work with faster_rcnn_inception rather than the ssd. Got the configuration file faster_rcnn_inception_v2_pets and configured all the paths but I get this error: (with the ssd model everything worked fine)
Traceback (most recent call last):
File "C:/Users/user/PycharmProjects/faster_rcnn_inception_500steps/3_train.py", line 154, in
tf.app.run()
File "C:\Users\user\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\platform\app.py", line 124, in run
_sys.exit(main(argv))
File "C:/Users/user/PycharmProjects/faster_rcnn_inception_500steps/3_train.py", line 115, in main
CLONE_ON_CPU, ps_tasks, worker_job_name, is_chief, TRAINING_DATA_DIR)
File "C:\tensorflow_git_models\models\research\object_detection\legacy\trainer.py", line 300, in train
train_config.optimizer)
File "C:\tensorflow_git_models\models\research\object_detection\builders\optimizer_builder.py", line 50, in build
learning_rate = _create_learning_rate(config.learning_rate)
File "C:\tensorflow_git_models\models\research\object_detection\builders\optimizer_builder.py", line 112, in _create_learning_rate
learning_rate_sequence, config.warmup)
File "C:\tensorflow_git_models\models\research\object_detection\utils\learning_schedules.py", line 160, in manual_stepping
raise ValueError('First step cannot be zero.')
ValueError: First step cannot be zero.
I changed all the paths in the 3_train.py in order for it to work with faster_rcnn_inception rather than the ssd. Got the configuration file faster_rcnn_inception_v2_pets and configured all the paths but I get this error: (with the ssd model everything worked fine)
Traceback (most recent call last): File "C:/Users/user/PycharmProjects/faster_rcnn_inception_500steps/3_train.py", line 154, in
tf.app.run()
File "C:\Users\user\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\platform\app.py", line 124, in run
_sys.exit(main(argv))
File "C:/Users/user/PycharmProjects/faster_rcnn_inception_500steps/3_train.py", line 115, in main
CLONE_ON_CPU, ps_tasks, worker_job_name, is_chief, TRAINING_DATA_DIR)
File "C:\tensorflow_git_models\models\research\object_detection\legacy\trainer.py", line 300, in train
train_config.optimizer)
File "C:\tensorflow_git_models\models\research\object_detection\builders\optimizer_builder.py", line 50, in build
learning_rate = _create_learning_rate(config.learning_rate)
File "C:\tensorflow_git_models\models\research\object_detection\builders\optimizer_builder.py", line 112, in _create_learning_rate
learning_rate_sequence, config.warmup)
File "C:\tensorflow_git_models\models\research\object_detection\utils\learning_schedules.py", line 160, in manual_stepping
raise ValueError('First step cannot be zero.')
ValueError: First step cannot be zero.
What should I do?