TypeError: Input 'split_dim' of 'Split' Op has type float32 that does not match expected type of int32.

[TessaJoseIgn]

Hi, I am getting the following error
TRAINING ROLO...
Traceback (most recent call last):
File "/home/###/threads/$$/venv/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 510, in _apply_op_helper
preferred_dtype=default_dtype)
File "/home/###/threads/$$/venv/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1146, in internal_convert_to_tensor
ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
File "/home/###/threads/$$/venv/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 983, in _TensorTensorConversionFunction
(dtype.name, t.dtype.name, str(t)))
ValueError: Tensor conversion requested dtype int32 for Tensor with dtype float32: 'Tensor("Reshape:0", shape=(6, 4102), dtype=float32)'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "experiments/training/ROLO_step6_train_20_exp1.py", line 332, in
main(' ')
File "experiments/training/ROLO_step6_train_20_exp1.py", line 329, in main
ROLO_TF(argvs)
File "experiments/training/ROLO_step6_train_20_exp1.py", line 95, in init
self.ROLO(argvs)
File "experiments/training/ROLO_step6_train_20_exp1.py", line 325, in ROLO
self.train_20()
File "experiments/training/ROLO_step6_train_20_exp1.py", line 222, in train_20
self.build_networks()
File "experiments/training/ROLO_step6_train_20_exp1.py", line 134, in build_networks
self.lstm_module = self.LSTM_single('lstm_test', self.x, self.istate, self.weights, self.biases)
File "experiments/training/ROLO_step6_train_20_exp1.py", line 105, in LSTM_single
_X = tf.split(0, self.num_steps, _X) # n_steps * (batch_size, num_input)
File "/home/###/threads/$$/venv/lib/python3.6/site-packages/tensorflow/python/ops/array_ops.py", line 1327, in split
axis=axis, num_split=num_or_size_splits, value=value, name=name)
File "/home/###/threads/$$/venv/lib/python3.6/site-packages/tensorflow/python/ops/gen_array_ops.py", line 8083, in split
"Split", split_dim=axis, value=value, num_split=num_split, name=name)
File "/home/###/threads/$$/venv/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 533, in _apply_op_helper
(prefix, dtypes.as_dtype(input_arg.type).name))
TypeError: Input 'split_dim' of 'Split' Op has type float32 that does not match expected type of int32.

[Niveditakatta]

Refer to this: tensorflow/tensorflow#6501

[abbasturkoglu]

Change this part:
_X = tf.split(0, self.num_steps, _X)

to this:
_X = tf.split(_X, self.num_steps, 0)