问题
I can train and evalaute a Tensorflow Estimator model without any problems. When I do prediction, this error arises:
InvalidArgumentError (see above for traceback): output_shape has incorrect number of elements: 68 should be: 2
[[Node: output = SparseToDense[T=DT_INT32, Tindices=DT_INT32, validate_indices=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"](ToInt32, ToInt32_1, ToInt32_2, bidirectional_rnn/bidirectional_rnn/fw/fw/time)]]
All of the model functions use the same architecture:
def _train_model_fn(features, labels, mode, params):
features = _network_fn(features, mode, params)
outputs = _get_output(features, params["output_layer"],
params["num_classes"])
predictions = {
"outputs": outputs
}
... # loss initialization and whatnot
def _eval_model_fn(features, labels, mode, params):
features = _network_fn(features, mode, params)
outputs = _get_output(features, params["output_layer"], params["num_classes"])
predictions = {
"outputs": outputs
}
... # loss initialization and whatnot
def _predict_model_fn(features, mode, params):
features = _network_fn(features, mode, params)
outputs = _get_output(features, params["output_layer"], params["num_classes"])
predictions = {
"outputs": outputs
}
...
Here's the predict code:
def predict(params, features, checkpoint_dir):
estimator = tf.estimator.Estimator(model_fn=_predict_model_fn,
params=params,
model_dir=checkpoint_dir)
predictions = estimator.predict(input_fn=_input_fn(features))
for i, p in enumerate(predictions):
print(i, p)
I also checked the shapes given every time the input passes a layer when training, and the same thing for predicting. They give the same shapes:
Training:
conv2d [1, 358, 358, 16]
max_pool2d [1, 179, 179, 16]
collapse_to_rnn_dims [1, 179, 2864]
birnn [1, 179, 64]
Prediction:
conv2d [1, 358, 358, 16]
max_pool2d [1, 179, 179, 16]
collapse_to_rnn_dims [1, 179, 2864]
birnn [1, 179, 64]
Here are the SparseTensors I passed to sparse_to_dense:
Training:
SparseTensor(indices=Tensor("CTCBeamSearchDecoder:0", shape=(?, 2), dtype=int64), values=Tensor("CTCBeamSearchDecoder:1", shape=(?,), dtype=int64), dense_shape=Tensor("CTCBeamSearchDecoder:2", shape=(2,), dtype=int64))
Evaluation:
SparseTensor(indices=Tensor("CTCBeamSearchDecoder:0", shape=(?, 2), dtype=int64), values=Tensor("CTCBeamSearchDecoder:1", shape=(?,), dtype=int64), dense_shape=Tensor("CTCBeamSearchDecoder:2", shape=(2,), dtype=int64))
Prediction:
SparseTensor(indices=Tensor("CTCBeamSearchDecoder:0", shape=(?, 2), dtype=int64), values=Tensor("CTCBeamSearchDecoder:1", shape=(?,), dtype=int64), dense_shape=Tensor("CTCBeamSearchDecoder:2", shape=(2,), dtype=int64))
Which are all pretty much the same.
Any reason why this is happening? Shouldn't the _predict_model_fn work given that it follows the same architecture as that of the other model_fns?
Here's the full stacktrace:
INFO:tensorflow:Using default config.
INFO:tensorflow:Using config: {'_log_step_count_steps': 100, '_keep_checkpoint_max': 5, '_task_type': 'worker', '_is_chief': True, '_service': None, '_save_summary_steps': 100, '_model_dir': 'checkpoint\\model-20180419-150303', '_task_id': 0, '_evaluation_master': '', '_tf_random_seed': None, '_cluster_spec': <tensorflow.python.training.server_lib.ClusterSpec object at 0x00000091F58B3080>, '_num_ps_replicas': 0, '_master': '', '_save_checkpoints_secs': 600, '_session_config': None, '_save_checkpoints_steps': None, '_keep_checkpoint_every_n_hours': 10000, '_global_id_in_cluster': 0, '_num_worker_replicas': 1}
INFO:tensorflow:Calling model_fn.
INFO:tensorflow:Done calling model_fn.
INFO:tensorflow:Graph was finalized.
INFO:tensorflow:Restoring parameters from checkpoint\model-20180419-150303\model.ckpt-1
INFO:tensorflow:Running local_init_op.
INFO:tensorflow:Done running local_init_op.
Process Process-2:
Traceback (most recent call last):
File "C:\Users\asus.11\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1361, in _do_call
return fn(*args)
File "C:\Users\asus.11\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1340, in _run_fn
target_list, status, run_metadata)
File "C:\Users\asus.11\Anaconda3\lib\site-packages\tensorflow\python\framework\errors_impl.py", line 516, in __exit__
c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: output_shape has incorrect number of elements: 68 should be: 2
[[Node: output = SparseToDense[T=DT_INT32, Tindices=DT_INT32, validate_indices=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"](ToInt32, ToInt32_1, ToInt32_2, bidirectional_rnn/bidirectional_rnn/fw/fw/time)]]
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "C:\Users\asus.11\Anaconda3\lib\multiprocessing\process.py", line 249, in _bootstrap
self.run()
File "C:\Users\asus.11\Anaconda3\lib\multiprocessing\process.py", line 93, in run
self._target(*self._args, **self._kwargs)
File "C:\Users\asus.11\Documents\Optimized_OCR\trainer\backend\train_ocr.py", line 42, in evaluate_model
evaluate(architecture_params, images, labels, checkpoint_dir)
File "C:\Users\asus.11\Documents\Optimized_OCR\trainer\backend\tf\experiment_ops.py", line 82, in evaluate
predict(params, features, checkpoint_dir)
File "C:\Users\asus.11\Documents\Optimized_OCR\trainer\backend\tf\experiment_ops.py", line 90, in predict
for i, p in enumerate(predictions):
File "C:\Users\asus.11\Anaconda3\lib\site-packages\tensorflow\python\estimator\estimator.py", line 492, in predict
preds_evaluated = mon_sess.run(predictions)
File "C:\Users\asus.11\Anaconda3\lib\site-packages\tensorflow\python\training\monitored_session.py", line 546, in run
run_metadata=run_metadata)
File "C:\Users\asus.11\Anaconda3\lib\site-packages\tensorflow\python\training\monitored_session.py", line 1022, in run
run_metadata=run_metadata)
File "C:\Users\asus.11\Anaconda3\lib\site-packages\tensorflow\python\training\monitored_session.py", line 1113, in run
raise six.reraise(*original_exc_info)
File "C:\Users\asus.11\Anaconda3\lib\site-packages\six.py", line 693, in reraise
raise value
File "C:\Users\asus.11\Anaconda3\lib\site-packages\tensorflow\python\training\monitored_session.py", line 1098, in run
return self._sess.run(*args, **kwargs)
File "C:\Users\asus.11\Anaconda3\lib\site-packages\tensorflow\python\training\monitored_session.py", line 1170, in run
run_metadata=run_metadata)
File "C:\Users\asus.11\Anaconda3\lib\site-packages\tensorflow\python\training\monitored_session.py", line 950, in run
return self._sess.run(*args, **kwargs)
File "C:\Users\asus.11\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 905, in run
run_metadata_ptr)
File "C:\Users\asus.11\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1137, in _run
feed_dict_tensor, options, run_metadata)
File "C:\Users\asus.11\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1355, in _do_run
options, run_metadata)
File "C:\Users\asus.11\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1374, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: output_shape has incorrect number of elements: 68 should be: 2
[[Node: output = SparseToDense[T=DT_INT32, Tindices=DT_INT32, validate_indices=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"](ToInt32, ToInt32_1, ToInt32_2, bidirectional_rnn/bidirectional_rnn/fw/fw/time)]]
Caused by op 'output', defined at:
File "<string>", line 1, in <module>
File "C:\Users\asus.11\Anaconda3\lib\multiprocessing\spawn.py", line 106, in spawn_main
exitcode = _main(fd)
File "C:\Users\asus.11\Anaconda3\lib\multiprocessing\spawn.py", line 119, in _main
return self._bootstrap()
File "C:\Users\asus.11\Anaconda3\lib\multiprocessing\process.py", line 249, in _bootstrap
self.run()
File "C:\Users\asus.11\Anaconda3\lib\multiprocessing\process.py", line 93, in run
self._target(*self._args, **self._kwargs)
File "C:\Users\asus.11\Documents\Optimized_OCR\trainer\backend\train_ocr.py", line 42, in evaluate_model
evaluate(architecture_params, images, labels, checkpoint_dir)
File "C:\Users\asus.11\Documents\Optimized_OCR\trainer\backend\tf\experiment_ops.py", line 82, in evaluate
predict(params, features, checkpoint_dir)
File "C:\Users\asus.11\Documents\Optimized_OCR\trainer\backend\tf\experiment_ops.py", line 90, in predict
for i, p in enumerate(predictions):
File "C:\Users\asus.11\Anaconda3\lib\site-packages\tensorflow\python\estimator\estimator.py", line 479, in predict
features, None, model_fn_lib.ModeKeys.PREDICT, self.config)
File "C:\Users\asus.11\Anaconda3\lib\site-packages\tensorflow\python\estimator\estimator.py", line 793, in _call_model_fn
model_fn_results = self._model_fn(features=features, **kwargs)
File "C:\Users\asus.11\Documents\Optimized_OCR\trainer\backend\tf\experiment_ops.py", line 217, in _predict_model_fn
outputs = _get_output(features, params["output_layer"], params["num_classes"])
File "C:\Users\asus.11\Documents\Optimized_OCR\trainer\backend\tf\experiment_ops.py", line 134, in _get_output
return _sparse_to_dense(decoded, name="output")
File "C:\Users\asus.11\Documents\Optimized_OCR\trainer\backend\tf\experiment_ops.py", line 38, in _sparse_to_dense
name=name)
File "C:\Users\asus.11\Anaconda3\lib\site-packages\tensorflow\python\ops\sparse_ops.py", line 791, in sparse_to_dense
name=name)
File "C:\Users\asus.11\Anaconda3\lib\site-packages\tensorflow\python\ops\gen_sparse_ops.py", line 2401, in _sparse_to_dense
name=name)
File "C:\Users\asus.11\Anaconda3\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "C:\Users\asus.11\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 3271, in create_op
op_def=op_def)
File "C:\Users\asus.11\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 1650, in __init__
self._traceback = self._graph._extract_stack() # pylint: disable=protected-access
InvalidArgumentError (see above for traceback): output_shape has incorrect number of elements: 68 should be: 2
[[Node: output = SparseToDense[T=DT_INT32, Tindices=DT_INT32, validate_indices=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"](ToInt32, ToInt32_1, ToInt32_2, bidirectional_rnn/bidirectional_rnn/fw/fw/time)]]
Update
I tried using the same architecture in a different training run, I encountered a different shap error:
InvalidArgumentError (see above for traceback): output_shape has incorrect number of elements: 69 should be: 2
[[Node: output = SparseToDense[T=DT_INT32, Tindices=DT_INT32, validate_indices=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"](ToInt32, ToInt32_1, ToInt32_2, bidirectional_rnn/bidirectional_rnn/fw/fw/time)]]
Apparently, the problem seems to lie in the ctc_beam_search_decoder. Switching to ctc_greedy_decoder doesn't help either. Why is it doing this?
More updates
I have uploaded the reproducible example: https://github.com/selcouthlyBlue/ShapeErrorReproduce
回答1:
I have finally figured out the error. The problem actually lies in the way I used sparse_to_dense. Apparently, the order I gave is wrong where the values came first before the shape:
return tf.sparse_to_dense(tf.to_int32(decoded[0].indices),
tf.to_int32(decoded[0].values),
tf.to_int32(decoded[0].dense_shape),
name="output")
The order should be (shape comes first before values):
return tf.sparse_to_dense(tf.to_int32(decoded[0].indices),
tf.to_int32(decoded[0].dense_shape),
tf.to_int32(decoded[0].values),
name="output")
来源：https://stackoverflow.com/questions/49911525/estimator-predict-has-shape-issues