ugnelis / tensorflow-rnn-ctc Goto Github PK
View Code? Open in Web Editor NEWRNN CTC by using TensorFlow.
License: MIT License
RNN CTC by using TensorFlow.
License: MIT License
Currently (9216d5a), training only with one file is made. Needs to be ability for training with multiple files.
when I replaced the data set with mine, I get this error:
2018-02-07 20:56:16.459860: W C:\tf_jenkins\home\workspace\rel-win\M\windows\PY\36\tensorflow\core\util\ctc\ctc_loss_calculator.cc:144] No valid path found.
2018-02-07 20:56:16.461720: W C:\tf_jenkins\home\workspace\rel-win\M\windows\PY\36\tensorflow\core\util\ctc\ctc_loss_calculator.cc:144] No valid path found.
2018-02-07 20:56:16.465147: W C:\tf_jenkins\home\workspace\rel-win\M\windows\PY\36\tensorflow\core\util\ctc\ctc_loss_calculator.cc:144] No valid path found.
2018-02-07 20:56:16.466100: W C:\tf_jenkins\home\workspace\rel-win\M\windows\PY\36\tensorflow\core\util\ctc\ctc_loss_calculator.cc:144] No valid path found.
2018-02-07 20:56:16.488530: W C:\tf_jenkins\home\workspace\rel-win\M\windows\PY\36\tensorflow\core\util\ctc\ctc_loss_calculator.cc:144] No valid path found.
what is the issue?
Separate train.py functions which can be use also elsewhere, and make utils file.
`Traceback (most recent call last):
File "C:\Python36\lib\site-packages\tensorflow\python\framework\common_shapes.py", line 686, in _cal
l_cpp_shape_fn_impl
input_tensors_as_shapes, status)
File "C:\Python36\lib\site-packages\tensorflow\python\framework\errors_impl.py", line 473, in __exit
__
c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: Dimensions must be equal, but are 100 an
d 63 for 'rnn/while/rnn/multi_rnn_cell/cell_0/cell_0/lstm_cell/MatMul_1' (op: 'MatMul') with input sha
pes: [?,100], [63,200].
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "train.py", line 244, in
tf.app.run()
File "C:\Python36\lib\site-packages\tensorflow\python\platform\app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "train.py", line 111, in main
outputs, _ = tf.nn.dynamic_rnn(stack, inputs_placeholder, sequence_length_placeholder, dtype=tf.fl
oat32)
File "C:\Python36\lib\site-packages\tensorflow\python\ops\rnn.py", line 614, in dynamic_rnn
dtype=dtype)
File "C:\Python36\lib\site-packages\tensorflow\python\ops\rnn.py", line 777, in dynamic_rnn_loop
swap_memory=swap_memory)
File "C:\Python36\lib\site-packages\tensorflow\python\ops\control_flow_ops.py", line 2816, in while
loop
result = loop_context.BuildLoop(cond, body, loop_vars, shape_invariants)
File "C:\Python36\lib\site-packages\tensorflow\python\ops\control_flow_ops.py", line 2640, in BuildL
oop
pred, body, original_loop_vars, loop_vars, shape_invariants)
File "C:\Python36\lib\site-packages\tensorflow\python\ops\control_flow_ops.py", line 2590, in _Build
Loop
body_result = body(*packed_vars_for_body)
File "C:\Python36\lib\site-packages\tensorflow\python\ops\rnn.py", line 760, in _time_step
skip_conditionals=True)
File "C:\Python36\lib\site-packages\tensorflow\python\ops\rnn.py", line 236, in _rnn_step
new_output, new_state = call_cell()
File "C:\Python36\lib\site-packages\tensorflow\python\ops\rnn.py", line 748, in
call_cell = lambda: cell(input_t, state)
File "C:\Python36\lib\site-packages\tensorflow\python\ops\rnn_cell_impl.py", line 183, in call
return super(RNNCell, self).call(inputs, state)
File "C:\Python36\lib\site-packages\tensorflow\python\layers\base.py", line 575, in call
outputs = self.call(inputs, *args, **kwargs)
File "C:\Python36\lib\site-packages\tensorflow\python\ops\rnn_cell_impl.py", line 1066, in call
cur_inp, new_state = cell(cur_inp, cur_state)
File "C:\Python36\lib\site-packages\tensorflow\python\ops\rnn_cell_impl.py", line 183, in call
return super(RNNCell, self).call(inputs, state)
File "C:\Python36\lib\site-packages\tensorflow\python\layers\base.py", line 575, in call
outputs = self.call(inputs, *args, **kwargs)
File "C:\Python36\lib\site-packages\tensorflow\python\ops\rnn_cell_impl.py", line 611, in call
lstm_matrix = self._linear1([inputs, m_prev])
File "C:\Python36\lib\site-packages\tensorflow\python\ops\rnn_cell_impl.py", line 1189, in call
res = math_ops.matmul(array_ops.concat(args, 1), self._weights)
File "C:\Python36\lib\site-packages\tensorflow\python\ops\math_ops.py", line 1891, in matmul
a, b, transpose_a=transpose_a, transpose_b=transpose_b, name=name)
File "C:\Python36\lib\site-packages\tensorflow\python\ops\gen_math_ops.py", line 2436, in _mat_mul
name=name)
File "C:\Python36\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 787, in _ap
ply_op_helper
op_def=op_def)
File "C:\Python36\lib\site-packages\tensorflow\python\framework\ops.py", line 2958, in create_op
set_shapes_for_outputs(ret)
File "C:\Python36\lib\site-packages\tensorflow\python\framework\ops.py", line 2209, in set_shapes_fo
r_outputs
shapes = shape_func(op)
File "C:\Python36\lib\site-packages\tensorflow\python\framework\ops.py", line 2159, in call_with_req
uiring
return call_cpp_shape_fn(op, require_shape_fn=True)
File "C:\Python36\lib\site-packages\tensorflow\python\framework\common_shapes.py", line 627, in call
_cpp_shape_fn
require_shape_fn)
File "C:\Python36\lib\site-packages\tensorflow\python\framework\common_shapes.py", line 691, in _cal
l_cpp_shape_fn_impl
raise ValueError(err.message)
ValueError: Dimensions must be equal, but are 100 and 63 for 'rnn/while/rnn/multi_rnn_cell/cell_0/cell
_0/lstm_cell/MatMul_1' (op: 'MatMul') with input shapes: [?,100], [63,200].`
Need to fix Travis CI failed error. Basically, .travis.yml is missing.
Make functionality for running trained model.
Is this code anywhere using batch normalization?
Add tests for train.py function:
Need functionality for saving trained TensorFlow model.
Got this info. at the end of the training:
2020-01-16 04:49:00,021 - root - INFO - Model saved in file: ./models/model.ckpt
I0116 04:49:00.021643 140352211462016 train.py:241] Model saved in file: ./models/model.ckpt
How to use the saved model for testing a .wav file? Is the code for testing the model already available?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.