gwtaylor / theano-rnn Goto Github PK

when i execute the program i get the following error i tried converting "fn" to float32 but the results are the same this is the error :
Traceback (most recent call last):
File "basic_rnn_example.py", line 40, in
non_sequences=[W, W_in, W_out]))
File "C:\Anaconda2\lib\site-packages\theano-0.7.0-py2.7.egg\theano\scan_module\scan.py", line 1042, in scan
scan_outs = local_op(_scan_inputs)
File "C:\Anaconda2\lib\site-packages\theano-0.7.0-py2.7.egg\theano\gof\op.py", line 507, in call
node = self.make_node(_inputs, **kwargs)
File "C:\Anaconda2\lib\site-packages\theano-0.7.0-py2.7.egg\theano\scan_module\scan_op.py", line 374, in make_node
inner_sitsot_out.type.dtype))
ValueError: When compiling the inner function of scan the following error has been encountered: The initial state (outputs_info in scan nomenclature) of variable IncSubtensor{Set;:int64:}.0 (argument number 1) has dtype float32, while the result of the inner function (fn) has dtype float64. This can happen if the inner function of scan results in an upcast or downcast.

Hi, I found the get_params method in getstatus is written as get_params, where a needless "" is written. The getstatus is in MetaRNN class. PLZ consider revising.

Hi, I found a exception below, when n_hidden=1 in rnn_minibatch.py . pls kindly let me know if you know how to solve it. thanks!

TypeError: Cannot convert Type TensorType(float64, 3D) (of Variable Subtensor{::int64}.0) into Type TensorType(float64, (False, False, True)). You can try to manually convert Subtensor{::int64}.0 into a TensorType(float64, (False, False, True)).

ubgpu@ubgpu:/github/theano-rnn$ sudo python basic_rnn_example.py
[sudo] password for ubgpu:
Sorry, try again.
[sudo] password for ubgpu:
Sorry, try again.
[sudo] password for ubgpu:
Using gpu device 0: GeForce GTX 970
Traceback (most recent call last):
File "basic_rnn_example.py", line 40, in
non_sequences=[W, W_in, W_out])
File "/usr/local/lib/python2.7/dist-packages/theano/scan_module/scan.py", line 1042, in scan
scan_outs = local_op(_scan_inputs)
File "/usr/local/lib/python2.7/dist-packages/theano/gof/op.py", line 507, in call
node = self.make_node(_inputs, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/theano/scan_module/scan_op.py", line 374, in make_node
inner_sitsot_out.type.dtype))
ValueError: When compiling the inner function of scan the following error has been encountered: The initial state (outputs_info in scan nomenclature) of variable IncSubtensor{Set;:int64:}.0 (argument number 1) has dtype float32, while the result of the inner function (fn) has dtype float64. This can happen if the inner function of scan results in an upcast or downcast.
ubgpu@ubgpu:/github/theano-rnn$ sudo python basic_rnn_example.py

Using gpu device 0: GeForce GTX 970
Traceback (most recent call last):
File "basic_rnn_example.py", line 40, in
non_sequences=[W, W_in, W_out])
File "/usr/local/lib/python2.7/dist-packages/theano/scan_module/scan.py", line 1042, in scan
scan_outs = local_op(_scan_inputs)
File "/usr/local/lib/python2.7/dist-packages/theano/gof/op.py", line 507, in call
node = self.make_node(_inputs, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/theano/scan_module/scan_op.py", line 374, in make_node
inner_sitsot_out.type.dtype))
ValueError: When compiling the inner function of scan the following error has been encountered: The initial state (outputs_info in scan nomenclature) of variable IncSubtensor{Set;:int64:}.0 (argument number 1) has dtype float32, while the result of the inner function (fn) has dtype float64. This can happen if the inner function of scan results in an upcast or downcast.
ubgpu@ubgpu:/github/theano-rnn$
ubgpu@ubgpu:/github/theano-rnn$
ubgpu@ubgpu:/github/theano-rnn$
ubgpu@ubgpu:/github/theano-rnn$ ll
total 108
drwxrwxr-x 3 ubgpu ubgpu 4096 6月 7 00:40 ./
drwxrwxr-x 255 ubgpu ubgpu 12288 7月 3 20:23 ../
-rw-rw-r-- 1 ubgpu ubgpu 1685 6月 7 00:40 basic_rnn_example.py
drwxrwxr-x 8 ubgpu ubgpu 4096 6月 7 00:40 .git/
-rw-rw-r-- 1 ubgpu ubgpu 232 6月 7 00:40 .gitignore
-rw-rw-r-- 1 ubgpu ubgpu 7374 6月 7 00:40 hf_example.py
-rw-rw-r-- 1 ubgpu ubgpu 1499 6月 7 00:40 License.md
-rw-rw-r-- 1 ubgpu ubgpu 1963 6月 7 00:40 README.md
-rw-rw-r-- 1 ubgpu ubgpu 39709 6月 7 00:40 rnn_minibatch.py
-rw-rw-r-- 1 ubgpu ubgpu 23215 6月 7 00:40 rnn.py
ubgpu@ubgpu:/github/theano-rnn$ sudo python hf_example.py
Using gpu device 0: GeForce GTX 970
Traceback (most recent call last):
File "hf_example.py", line 12, in
from hf import SequenceDataset, hf_optimizer
ImportError: No module named hf
ubgpu@ubgpu:/github/theano-rnn$