- 15 3月, 2012 18 次提交
-
-
由 Olivier Delalleau 提交于
enable_sparse is indeed a Boolean
-
由 Olivier Delalleau 提交于
-
由 Olivier Delalleau 提交于
Fix composite new inputs
-
由 Frederic 提交于
-
由 Frederic 提交于
It happen in a particular execution order of this optimization and the element-wise fusion optimization when upcasting some inputs to float32 (to compute them on the gpu). (Frederic B., reported by Sander Dieleman)
-
由 Frederic 提交于
-
由 Frederic 提交于
-
由 Olivier Delalleau 提交于
Fix for win64
-
由 lamblin 提交于
New interface for scan
-
由 Razvan Pascanu 提交于
-
由 Razvan Pascanu 提交于
-
由 Razvan Pascanu 提交于
-
由 Olivier Delalleau 提交于
Gpuconv
-
由 Frederic 提交于
-
由 Frederic 提交于
-
由 Frederic 提交于
-
由 nouiz 提交于
fixed bug in min_informative_str
-
由 Ian Goodfellow 提交于
-
- 14 3月, 2012 22 次提交
-
-
由 Frederic 提交于
-
由 nouiz 提交于
Fix syntax error, remove unused import.
-
由 Pascal Lamblin 提交于
-
由 Pascal Lamblin 提交于
-
由 Frederic 提交于
-
由 Pascal Lamblin 提交于
This is temporary, as we should remove NONE_CODE ultimately.
-
由 Pascal Lamblin 提交于
-
由 Pascal Lamblin 提交于
-
由 Frederic 提交于
-
由 Razvan Pascanu 提交于
-
由 Razvan Pascanu 提交于
-
由 Razvan Pascanu 提交于
I used to call as_tensor_variable which is not ok for sparse or random generators
-
由 Razvan Pascanu 提交于
-
由 Razvan Pascanu 提交于
-
由 Razvan Pascanu 提交于
node.
-
由 Razvan Pascanu 提交于
-
由 Razvan Pascanu 提交于
sequences are not a list of dictionary anymore, but a list of tensors, the original tensors.
-
由 Razvan Pascanu 提交于
-
由 Razvan Pascanu 提交于
Now scan requires the user to say the number of steps. In case of outputs that do not feed anything in, if the user does not provide any information then it is assumed that you want all intermediate steps.
-
由 Razvan Pascanu 提交于
-
由 lamblin 提交于
fix crash introduced during pep8 fix.
-
由 Frederic 提交于
-