Я пытаюсь обучить embedded_ssd_mobilenet_v1_coco.config с Tensorflow, используя учебник EdjeElectronics и fine_tune_checkpoints от zhoujustin ( все ссылки ниже ), чтобы соответствовать 256x256 и Depth_multiplier = 0,125, необходимые для AIY Vision Kit. Но выдает следующую ошибку:
D: \ ObjectDetection \ models \ research \ object_detection> python train.py --logtostderr --train_dir = training / --pipeline_config_path = training / embedded_ssd_mobilenet_v1_coco.config
WARNING:tensorflow:From D:\ObjectDetection\models\research\object_detection\trainer.py:210: create_global_step (from tensorflow.contrib.framework.python.ops.variables) is deprecated and will be removed in a future version.
Instructions for updating:
Please switch to tf.train.create_global_step
INFO:tensorflow:depth of additional conv before box predictor: 0
INFO:tensorflow:depth of additional conv before box predictor: 0
INFO:tensorflow:depth of additional conv before box predictor: 0
INFO:tensorflow:depth of additional conv before box predictor: 0
INFO:tensorflow:depth of additional conv before box predictor: 0
Traceback (most recent call last):
File "train.py", line 163, in
tf.app.run()
File "C:\Users\Asus\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\platform\app.py", line 124, in run
_sys.exit(main(argv))
File "train.py", line 159, in main
worker_job_name, is_chief, FLAGS.train_dir)
File "D:\ObjectDetection\models\research\object_detection\trainer.py", line 228, in train
clones = model_deploy.create_clones(deploy_config, model_fn, [input_queue])
File "D:\ObjectDetection\models\research\slim\deployment\model_deploy.py", line 193, in create_clones
outputs = model_fn(*args, **kwargs)
File "D:\ObjectDetection\models\research\object_detection\trainer.py", line 167, in _create_losses
losses_dict = detection_model.loss(prediction_dict)
File "D:\ObjectDetection\models\research\object_detection\meta_architectures\ssd_meta_arch.py", line 474, in loss
location_losses, cls_losses, prediction_dict, match_list)
File "D:\ObjectDetection\models\research\object_detection\meta_architectures\ssd_meta_arch.py", line 640, in _apply_hard_mining
match_list=match_list)
File "D:\ObjectDetection\models\research\object_detection\core\losses.py", line 515, in call
location_losses = tf.unstack(location_losses)
File "C:\Users\Asus\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\ops\array_ops.py", line 1054, in unstack
(axis, -value_shape.ndims, value_shape.ndims))
ValueError: axis = 0 not in [0, 0)
Можете ли вы, ребята, помочь мне? Спасибо.
Ссылки
Файлы конфигурации: https://github.com/tensorflow/models/blob/master/research/object_detection/samples/configs/embedded_ssd_mobilenet_v1_coco.config
Учебное пособие по тензорному потоку от EdjeElectronics: https://github.com/EdjeElectronics/TensorFlow-Object-Detection-API-Tutorial-Train-Multiple-Objects-Windows-10
fine_tune_checkpoint от zhoujustin: https://drive.google.com/file/d/1_MeZ8kvmpNibPZvSJGnwKNRATeuyxNtu/view