TypeError: Received unknown keyword arguments: {'epochs': 5}

Question

TypeError: Received unknown keyword arguments: {'epochs': 5}

analyzehim opened this issue 6 years ago · comments

Hello!
Thanks for you work, it's really nice (especcially a idea of generating kanye songs :) )

But i have a trouble,
I'm trying to training model (by python model ), and after Alright, building the list of all the rhymes and show all bigram, get this:

Traceback (most recent call last):
File "model.py", line 300, in
main(depth, train_mode)
File "model.py", line 290, in main
train(x_data, y_data, model)
File "model.py", line 273, in train
verbose=1)
File "/usr/local/lib/python2.7/dist-packages/keras/models.py", line 661, in fit
str(kwargs))
TypeError: Received unknown keyword arguments: {'epochs': 5}

My environment:
Ubuntu 64bit,
Python 2.7.6 (default, Oct 26 2016, 20:30:19)
[GCC 4.8.4]

Robbie Barrat · Answer 1 · Sat Dec 23 2017 10:05:53 GMT+0800 (China Standard Time)

What version of keras are you using?
run python, and then

import keras

keras.__version__

you may need to update keras...

L4rs · Answer 2 · Sat Dec 23 2017 22:19:27 GMT+0800 (China Standard Time)

My keras Version is 1.2.2.
Should I use a 2.1.2 version?

Robbie Barrat · Answer 3 · Sun Dec 24 2017 08:18:21 GMT+0800 (China Standard Time)

before you update keras; try this:

on line 272; where it says

model.fit(np.array(x_data), np.array(y_data),
			  batch_size=2,
			  epochs=5,
			  verbose=1)

change epochs=5, to nb_epoch=5, - i think that might work with your version

L4rs · Answer 4 · Tue Dec 26 2017 15:22:42 GMT+0800 (China Standard Time)

At first, I try you assumption (epochs -> nb_epochs), get the same error.
After that, I updated keras to 2.1.2 (numpy to 1.13.3), and get this:

Using TensorFlow backend.
Traceback (most recent call last):
File "model.py", line 300, in
main(depth, train_mode)
File "model.py", line 277, in main
model = create_network(depth)
File "model.py", line 20, in create_network
model.add(LSTM(4, input_shape=(2, 2), return_sequences=True))
File "/usr/local/lib/python2.7/dist-packages/keras/models.py", line 464, in add
layer(x)
File "/usr/local/lib/python2.7/dist-packages/keras/layers/recurrent.py", line 482, in call
return super(RNN, self).call(inputs, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/topology.py", line 576, in call
self.build(input_shapes[0])
File "/usr/local/lib/python2.7/dist-packages/keras/layers/recurrent.py", line 444, in build
self.cell.build(step_input_shape)
File "/usr/local/lib/python2.7/dist-packages/keras/layers/recurrent.py", line 1738, in build
constraint=self.bias_constraint)
File "/usr/local/lib/python2.7/dist-packages/keras/legacy/interfaces.py", line 87, in wrapper
return func(*args, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/topology.py", line 397, in add_weight
weight = K.variable(initializer(shape),
File "/usr/local/lib/python2.7/dist-packages/keras/layers/recurrent.py", line 1730, in bias_initializer
self.bias_initializer((self.units * 2,), *args, **kwargs),
File "/usr/local/lib/python2.7/dist-packages/keras/backend/tensorflow_backend.py", line 1768, in concatenate
return tf.concat([to_dense(x) for x in tensors], axis)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/array_ops.py", line 692, in concat
dtype=dtypes.int32).get_shape(
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 628, in convert_to_tensor
ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/constant_op.py", line 180, in _constant_tensor_conversion_function
return constant(v, dtype=dtype, name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/constant_op.py", line 163, in constant
tensor_util.make_tensor_proto(value, dtype=dtype, shape=shape))
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/tensor_util.py", line 353, in make_tensor_proto
_AssertCompatible(values, dtype)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/tensor_util.py", line 290, in _AssertCompatible
(dtype.name, repr(mismatch), type(mismatch).name))
TypeError: Expected int32, got list containing Tensors of type '_Message' instead.

Robbie Barrat · Answer 5 · Wed Dec 27 2017 03:26:04 GMT+0800 (China Standard Time)

here - it works on my machine and these are my versions of everything

python 2.7
keras 2.0.8
tensorflow 1.4.1
numpy 1.13.0

I'm sorry that this isn't the most helpful response - but I don't know what else to try except for installing these versions of the packages and running the program then.

L4rs · Answer 6 · Thu Jan 04 2018 04:01:50 GMT+0800 (China Standard Time)

Hmmm...
Thanks for the answer, anyway!
Could you give me the CPU/GPU/RAM/HDD characteristic of your machie, please?

I run you neural network on very weak virtual machine, maybe this is the reason.

Robbie Barrat · Answer 7 · Thu Jan 04 2018 04:04:27 GMT+0800 (China Standard Time)

I developed / tested this on a super old thinkpad - right now it's running on my work computer which is pretty beefy (I work at NVIDIA right now) - so I've got 2 titans, an i7, and 64 gb of ram... hold up let me get an old commit you could run on your computer...

if you have tensorflow_gpu installed; I'd say uninstall that with pip uninstall tensorflow-gpu and then do pip install tensorflow so it will run on your CPU...

Virtual machine could be something to do with it, especially if you're trying to use tf gpu...

Robbie Barrat · Answer 8 · Thu Jan 04 2018 04:06:03 GMT+0800 (China Standard Time)

try to use the version here; before i did the keras rewrite i wrote it in pybrain, so you'll have to install all the stuff in requirements.txt with pip -r install requirements.txt (i think), but you could run this version on a toaster;

https://github.com/robbiebarrat/rapping-neural-network/tree/d1d341dd6f46263f790a3dc5c65a70d9a4eb0492