InvalidArgumentError when using do_single_file_inference()

[wonchang]

hi all,

I was trying to use:

do_single_file_inference() from DeepSpeech.py

like

do_single_file_inference('audio/4507-16021-0012.wav')

but I got an error like:

E Checkpoint directory (/root/.local/share/deepspeech/checkpoints) does not contain a valid checkpoint state.
INFO:tensorflow:Restoring parameters from checkpoint/model.ckpt-97999

InvalidArgumentErrorTraceback (most recent call last)
/opt/conda/lib/python3.6/site-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args)
1322 try:
-> 1323 return fn(*args)
1324 except errors.OpError as e:

/opt/conda/lib/python3.6/site-packages/tensorflow/python/client/session.py in _run_fn(session, feed_dict, fetch_list, target_list, options, run_metadata)
1301 feed_dict, fetch_list, target_list,
-> 1302 status, run_metadata)
1303

/opt/conda/lib/python3.6/site-packages/tensorflow/python/framework/errors_impl.py in exit(self, type_arg, value_arg, traceback_arg)
472 compat.as_text(c_api.TF_Message(self.status.status)),
–> 473 c_api.TF_GetCode(self.status.status))
474 # Delete the underlying status object from memory otherwise it stays alive

InvalidArgumentError: Shapes of all inputs must match: values[0].shape = [1,30] != values[1].shape = [1,31]
[[Node: output_node = Pack[N=5, T=DT_INT64, axis=0, _device="/job:localhost/replica:0/task:0/device:GPU:0"](SparseToDense/_59, SparseToDense_1/_61, SparseToDense_2/_63, SparseToDense_3/_65, SparseToDense_4/_67)]]
[[Node: output_node/_69 = _Recvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name=“edge_387_output_node”, tensor_type=DT_INT64, _device="/job:localhost/replica:0/task:0/device:CPU:0"]]

During handling of the above exception, another exception occurred:

InvalidArgumentErrorTraceback (most recent call last)
in ()
----> 1 do_single_file_inference(‘audio/4507-16021-0012.wav’)

in do_single_file_inference(input_file_path)
23 output = session.run(outputs[‘outputs’], feed_dict = {
24 inputs[‘input’]: [mfcc],
—> 25 inputs[‘input_lengths’]: [len(mfcc)],
26 })
27

/opt/conda/lib/python3.6/site-packages/tensorflow/python/client/session.py in run(self, fetches, feed_dict, options, run_metadata)
887 try:
888 result = self._run(None, fetches, feed_dict, options_ptr,
–> 889 run_metadata_ptr)
890 if run_metadata:
891 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)

/opt/conda/lib/python3.6/site-packages/tensorflow/python/client/session.py in _run(self, handle, fetches, feed_dict, options, run_metadata)
1118 if final_fetches or final_targets or (handle and feed_dict_tensor):
1119 results = self._do_run(handle, final_targets, final_fetches,
-> 1120 feed_dict_tensor, options, run_metadata)
1121 else:
1122 results = []

/opt/conda/lib/python3.6/site-packages/tensorflow/python/client/session.py in _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)
1315 if handle is None:
1316 return self._do_call(_run_fn, self._session, feeds, fetches, targets,
-> 1317 options, run_metadata)
1318 else:
1319 return self._do_call(_prun_fn, self._session, handle, feeds, fetches)

/opt/conda/lib/python3.6/site-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args)
1334 except KeyError:
1335 pass
-> 1336 raise type(e)(node_def, op, message)
1337
1338 def _extend_graph(self):

InvalidArgumentError: Shapes of all inputs must match: values[0].shape = [1,30] != values[1].shape = [1,31]
[[Node: output_node = Pack[N=5, T=DT_INT64, axis=0, _device="/job:localhost/replica:0/task:0/device:GPU:0"](SparseToDense/_59, SparseToDense_1/_61, SparseToDense_2/_63, SparseToDense_3/_65, SparseToDense_4/_67)]]
[[Node: output_node/_69 = _Recvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name=“edge_387_output_node”, tensor_type=DT_INT64, _device="/job:localhost/replica:0/task:0/device:CPU:0"]]

Caused by op ‘output_node’, defined at:
File “/opt/conda/lib/python3.6/runpy.py”, line 193, in _run_module_as_main
"main", mod_spec)
File “/opt/conda/lib/python3.6/runpy.py”, line 85, in _run_code
exec(code, run_globals)
File “/opt/conda/lib/python3.6/site-packages/ipykernel_launcher.py”, line 16, in
app.launch_new_instance()
File “/opt/conda/lib/python3.6/site-packages/traitlets/config/application.py”, line 658, in launch_instance
app.start()
File “/opt/conda/lib/python3.6/site-packages/ipykernel/kernelapp.py”, line 478, in start
self.io_loop.start()
File “/opt/conda/lib/python3.6/site-packages/zmq/eventloop/ioloop.py”, line 177, in start
super(ZMQIOLoop, self).start()
File “/opt/conda/lib/python3.6/site-packages/tornado/ioloop.py”, line 888, in start
handler_func(fd_obj, events)
File “/opt/conda/lib/python3.6/site-packages/tornado/stack_context.py”, line 277, in null_wrapper
return fn(*args, **kwargs)
File “/opt/conda/lib/python3.6/site-packages/zmq/eventloop/zmqstream.py”, line 440, in _handle_events
self._handle_recv()
File “/opt/conda/lib/python3.6/site-packages/zmq/eventloop/zmqstream.py”, line 472, in _handle_recv
self._run_callback(callback, msg)
File “/opt/conda/lib/python3.6/site-packages/zmq/eventloop/zmqstream.py”, line 414, in _run_callback
callback(*args, **kwargs)
File “/opt/conda/lib/python3.6/site-packages/tornado/stack_context.py”, line 277, in null_wrapper
return fn(*args, **kwargs)
File “/opt/conda/lib/python3.6/site-packages/ipykernel/kernelbase.py”, line 281, in dispatcher
return self.dispatch_shell(stream, msg)
File “/opt/conda/lib/python3.6/site-packages/ipykernel/kernelbase.py”, line 232, in dispatch_shell
handler(stream, idents, msg)
File “/opt/conda/lib/python3.6/site-packages/ipykernel/kernelbase.py”, line 397, in execute_request
user_expressions, allow_stdin)
File “/opt/conda/lib/python3.6/site-packages/ipykernel/ipkernel.py”, line 208, in do_execute
res = shell.run_cell(code, store_history=store_history, silent=silent)
File “/opt/conda/lib/python3.6/site-packages/ipykernel/zmqshell.py”, line 533, in run_cell
return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
File “/opt/conda/lib/python3.6/site-packages/IPython/core/interactiveshell.py”, line 2728, in run_cell
interactivity=interactivity, compiler=compiler, result=result)
File “/opt/conda/lib/python3.6/site-packages/IPython/core/interactiveshell.py”, line 2856, in run_ast_nodes
if self.run_code(code, result):
File “/opt/conda/lib/python3.6/site-packages/IPython/core/interactiveshell.py”, line 2910, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File “”, line 1, in
do_single_file_inference(‘audio/4507-16021-0012.wav’)
File “”, line 4, in do_single_file_inference
inputs, outputs = create_inference_graph(batch_size=1, use_new_decoder=False, top_paths=5)
File “”, line 15, in create_inference_graph
[tf.sparse_tensor_to_dense(sparse_tensor) for sparse_tensor in decoded], name=‘output_node’)
File “/opt/conda/lib/python3.6/site-packages/tensorflow/python/framework/ops.py”, line 836, in convert_to_tensor
as_ref=False)
File “/opt/conda/lib/python3.6/site-packages/tensorflow/python/framework/ops.py”, line 926, in internal_convert_to_tensor
ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
File “/opt/conda/lib/python3.6/site-packages/tensorflow/python/ops/array_ops.py”, line 970, in _autopacking_conversion_function
return _autopacking_helper(v, inferred_dtype, name or “packed”)
File “/opt/conda/lib/python3.6/site-packages/tensorflow/python/ops/array_ops.py”, line 933, in _autopacking_helper
return gen_array_ops._pack(elems_as_tensors, name=scope)
File “/opt/conda/lib/python3.6/site-packages/tensorflow/python/ops/gen_array_ops.py”, line 2872, in _pack
"Pack", values=values, axis=axis, name=name)
File “/opt/conda/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py”, line 787, in _apply_op_helper
op_def=op_def)
File “/opt/conda/lib/python3.6/site-packages/tensorflow/python/framework/ops.py”, line 2956, in create_op
op_def=op_def)
File “/opt/conda/lib/python3.6/site-packages/tensorflow/python/framework/ops.py”, line 1470, in init
self._traceback = self._graph._extract_stack() # pylint: disable=protected-access

InvalidArgumentError (see above for traceback): Shapes of all inputs must match: values[0].shape = [1,30] != values[1].shape = [1,31]
[[Node: output_node = Pack[N=5, T=DT_INT64, axis=0, _device="/job:localhost/replica:0/task:0/device:GPU:0"](SparseToDense/_59, SparseToDense_1/_61, SparseToDense_2/_63, SparseToDense_3/_65, SparseToDense_4/_67)]]
[[Node: output_node/_69 = _Recvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name=“edge_387_output_node”, tensor_type=DT_INT64, _device="/job:localhost/replica:0/task:0/device:CPU:0"]]

What I don’t really understand is: InvalidArgumentError: Shapes of all inputs must match: values[0].shape = [1,30] != values[1].shape = [1,31]

what is happening here?

[kdavis]

Did you use the command line argument --one_shot_infer when you called DeepSpeech.py on the command line?

[reuben]

The function depends on the values of the DeepSpeech.py command line flags, in particular the --checkpoint_dir flag. If you’re calling the function directly, you need to make sure you’re setting up the environment first.

As Kelly already said, you could also just use the --one_shot_infer flag.