- 20 6月, 2012 4 次提交
-
-
由 James Bergstra 提交于
-
由 James Bergstra 提交于
-
由 James Bergstra 提交于
-
由 James Bergstra 提交于
-
- 19 6月, 2012 10 次提交
-
-
由 James Bergstra 提交于
-
由 James Bergstra 提交于
-
由 lamblin 提交于
fix context problem with pycuda by checking it is imported before.
-
由 Frederic 提交于
-
由 goodfeli 提交于
Opt
-
由 Frederic 提交于
We already checked that the node is still in the env before we process it.
-
由 Frederic 提交于
-
由 Frederic 提交于
-
由 Frederic 提交于
-
由 Frederic 提交于
Also add the pycuda.init flag to force its import. It is not needed to set it to True in the buildbot, as all test file get imported before test start to run. So this init PyCUDA first if the theano flag device and init_gpu_device are not used.
-
- 16 6月, 2012 9 次提交
- 15 6月, 2012 17 次提交
-
-
由 lamblin 提交于
Small
-
由 Frederic 提交于
-
由 lamblin 提交于
Time opt
-
由 Frederic 提交于
-
由 Razvan Pascanu 提交于
-
由 Razvan Pascanu 提交于
The bug was reported by Nicolas, and it happens when you have a single tap for a sequence that is different from 0.
-
由 Frederic 提交于
-
由 Frederic 提交于
-
由 Frederic 提交于
Accept profile=False and when we profile, preload the c module cache to don't have it include in optimization time.
-
由 Frederic 提交于
-
由 Frederic 提交于
-
由 Frederic 提交于
-
由 Frederic 提交于
-
由 Frederic 提交于
-
由 Frederic 提交于
-
由 Frederic 提交于
-
由 Frederic 提交于
-