Я использую обнаружение объекта Тензор потока для обучения пользовательских данных на windows.
Когда я использую эту команду для обучения моей модели:
python model_main.py --pipeline_config_path = training / ssd_inception_v2_coco.config --model_dir = training / --num_train_steps = 200000 --alsologtostderr
Предупреждающее сообщение:
Instructions for updating:
Use tf.data.experimental.parallel_interleave(...).
WARNING:tensorflow:From E:\Anaconda3\lib\site-packages\tensorflow\python\ops\sparse_ops.py:1165: sparse_to_dense (from tensorflow.python.ops.sparse_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Create a tf.sparse.SparseTensor and use tf.sparse.to_dense instead.
WARNING:tensorflow:From E:\test_opencv\models-master\research\object_detection\builders\dataset_builder.py:158: batch_and_drop_remainder (from tensorflow.contrib.data.python.ops.batching) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.data.Dataset.batch(..., drop_remainder=True).
WARNING:root:Variable [BoxPredictor_0/ClassPredictor/biases] is available in checkpoint, but has an incompatible shape with model variable. Checkpoint shape: [[273]], model variable shape: [[21]]. This variable will not be initialized from the check
point.
WARNING:root:Variable [BoxPredictor_0/ClassPredictor/weights] is available in checkpoint, but has an incompatible shape with model variable. Checkpoint shape: [[3, 3, 576, 273]], model variable shape: [[3, 3, 576, 21]]. This variable will not be ini
tialized from the checkpoint.
WARNING:root:Variable [BoxPredictor_1/ClassPredictor/biases] is available in checkpoint, but has an incompatible shape with model variable. Checkpoint shape: [[546]], model variable shape: [[42]]. This variable will not be initialized from the check
point.
WARNING:root:Variable [BoxPredictor_1/ClassPredictor/weights] is available in checkpoint, but has an incompatible shape with model variable. Checkpoint shape: [[3, 3, 1024, 546]], model variable shape: [[3, 3, 1024, 42]]. This variable will not be i
nitialized from the checkpoint.
WARNING:root:Variable [BoxPredictor_2/ClassPredictor/biases] is available in checkpoint, but has an incompatible shape with model variable. Checkpoint shape: [[546]], model variable shape: [[42]]. This variable will not be initialized from the check
point.
WARNING:root:Variable [BoxPredictor_2/ClassPredictor/weights] is available in checkpoint, but has an incompatible shape with model variable. Checkpoint shape: [[3, 3, 512, 546]], model variable shape: [[3, 3, 512, 42]]. This variable will not be ini
tialized from the checkpoint.
WARNING:root:Variable [BoxPredictor_3/ClassPredictor/biases] is available in checkpoint, but has an incompatible shape with model variable. Checkpoint shape: [[546]], model variable shape: [[42]]. This variable will not be initialized from the check
point.
WARNING:root:Variable [BoxPredictor_3/ClassPredictor/weights] is available in checkpoint, but has an incompatible shape with model variable. Checkpoint shape: [[3, 3, 256, 546]], model variable shape: [[3, 3, 256, 42]]. This variable will not be ini
tialized from the checkpoint.
WARNING:root:Variable [BoxPredictor_4/ClassPredictor/biases] is available in checkpoint, but has an incompatible shape with model variable. Checkpoint shape: [[546]], model variable shape: [[42]]. This variable will not be initialized from the check
point.
WARNING:root:Variable [BoxPredictor_4/ClassPredictor/weights] is available in checkpoint, but has an incompatible shape with model variable. Checkpoint shape: [[3, 3, 256, 546]], model variable shape: [[3, 3, 256, 42]]. This variable will not be ini
tialized from the checkpoint.
WARNING:root:Variable [BoxPredictor_5/ClassPredictor/biases] is available in checkpoint, but has an incompatible shape with model variable. Checkpoint shape: [[546]], model variable shape: [[42]]. This variable will not be initialized from the check
point.
WARNING:root:Variable [BoxPredictor_5/ClassPredictor/weights] is available in checkpoint, but has an incompatible shape with model variable. Checkpoint shape: [[3, 3, 128, 546]], model variable shape: [[3, 3, 128, 42]]. This variable will not be ini
tialized from the checkpoint.
WARNING:root:Variable [global_step] is not available in checkpoint
1013 * Когда появилось предупреждение, я думал, что предупреждение
WARNING:root:Variable [global_step] is not available in checkpoint никогда не исчезнет go, пока ошибка не будет устранена, но через некоторое время модель начнет тренироваться, это очень странно.
Если я этого не сделаю используйте эту конфигурацию load_all_detection_checkpoint_vars: true в файле конфигурации конвейера ssd_inception_v2_coco.config, я не получаю это предупреждение, но если я добавлю эту конфигурацию load_all_detection_checkpoint_vars: true в файл конфигурации конвейера, я получу предупреждение.
Так как исправить предупреждение?