TensorFlow Object Detection API training error

Question

When I used ssd_mobilenet_v2_320x320_coco17_tpu-8.config to train the model to gain my weights and bias，the error occurred:

```python
INFO:tensorflow:depth of additional conv before box predictor: 0
I0907 12:25:05.139600 140082463876864 convolutional_keras_box_predictor.py:154] depth of additional conv before box predictor: 0
INFO:tensorflow:depth of additional conv before box predictor: 0
I0907 12:25:05.139784 140082463876864 convolutional_keras_box_predictor.py:154] depth of additional conv before box predictor: 0
INFO:tensorflow:depth of additional conv before box predictor: 0
I0907 12:25:05.139850 140082463876864 convolutional_keras_box_predictor.py:154] depth of additional conv before box predictor: 0
INFO:tensorflow:depth of additional conv before box predictor: 0
I0907 12:25:05.139908 140082463876864 convolutional_keras_box_predictor.py:154] depth of additional conv before box predictor: 0
INFO:tensorflow:depth of additional conv before box predictor: 0
I0907 12:25:05.139959 140082463876864 convolutional_keras_box_predictor.py:154] depth of additional conv before box predictor: 0
INFO:tensorflow:depth of additional conv before box predictor: 0
I0907 12:25:05.140012 140082463876864 convolutional_keras_box_predictor.py:154] depth of additional conv before box predictor: 0
Traceback (most recent call last):
  File "model_main_tf2.py", line 115, in <module>
    tf.compat.v1.app.run()
  File "/home/hh/anaconda3/envs/tensorflow/lib/python3.7/site-packages/tensorflow/python/platform/app.py", line 40, in run
    _run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
  File "/home/hh/anaconda3/envs/tensorflow/lib/python3.7/site-packages/absl/app.py", line 303, in run
    _run_main(main, args)
  File "/home/hh/anaconda3/envs/tensorflow/lib/python3.7/site-packages/absl/app.py", line 251, in _run_main
    sys.exit(main(argv))
  File "model_main_tf2.py", line 112, in main
    record_summaries=FLAGS.record_summaries)
  File "/home/hh/anaconda3/envs/tensorflow/lib/python3.7/site-packages/object_detection/model_lib_v2.py", line 677, in train_loop
    losses_dict = _dist_train_step(train_input_iter)
  File "/home/hh/anaconda3/envs/tensorflow/lib/python3.7/site-packages/tensorflow/python/eager/def_function.py", line 885, in __call__
    result = self._call(*args, **kwds)
  File "/home/hh/anaconda3/envs/tensorflow/lib/python3.7/site-packages/tensorflow/python/eager/def_function.py", line 950, in _call
    return self._stateless_fn(*args, **kwds)
  File "/home/hh/anaconda3/envs/tensorflow/lib/python3.7/site-packages/tensorflow/python/eager/function.py", line 3040, in __call__
    filtered_flat_args, captured_inputs=graph_function.captured_inputs)  # pylint: disable=protected-access
  File "/home/hh/anaconda3/envs/tensorflow/lib/python3.7/site-packages/tensorflow/python/eager/function.py", line 1964, in _call_flat
    ctx, args, cancellation_manager=cancellation_manager))
  File "/home/hh/anaconda3/envs/tensorflow/lib/python3.7/site-packages/tensorflow/python/eager/function.py", line 596, in call
    ctx=ctx)
  File "/home/hh/anaconda3/envs/tensorflow/lib/python3.7/site-packages/tensorflow/python/eager/execute.py", line 60, in quick_execute
    inputs, attrs, num_outputs)
tensorflow.python.framework.errors_impl.InvalidArgumentError:  indices[1] = 1 is not in [0, 1)
     [[{{node GatherV2_7}}]]
     [[MultiDeviceIteratorGetNextFromShard]]
     [[RemoteCall]]
     [[while/body/_1/IteratorGetNext]] [Op:__inference__dist_train_step_34882]
 
Function call stack:
_dist_train_step

.......
.......
I try to solve the problem by myself,but in vain.So I want to gain the solution by searching on the internet.The only one I can find is this:https://stackoverflow.com/questions/48847365/tensorflow-object-detection-api-training-error.So simliar was it to my condition that I once thought he was the

angle of the God to save me.What a pity!It didn't work,and I fell into the hell again.The gods in the commuity,relief me!

Answer 1

你好，我是有问必答小助手，非常抱歉，本次您提出的有问必答问题，技术专家团超时未为您做出解答


本次提问扣除的有问必答次数，将会以问答VIP体验卡（1次有问必答机会、商城购买实体图书享受95折优惠）的形式为您补发到账户。


因为有问必答VIP体验卡有效期仅有1天，您在需要使用的时候【私信】联系我，我会为您补发。