merge

doc/index.txt

@@ -36,6 +36,7 @@ Roughly in order of what you'll want to check out:
 * :ref:`libdoc` -- All Theano's functionality, module by module.
 * :ref:`extending` -- Learn to add a Type, Op, or graph optimization.
 * :ref:`internal` -- How to maintaining Theano, LISA-specific tips, and more...
+* `API <api/>`_ -- The automatically-generated API
 
 You can download the latest `PDF documentation <http://deeplearning.net/theanodoc/theano.pdf>`_, rather than reading it online.
 
@@ -46,7 +47,7 @@ Community
 
 * Register and post to `theano-dev`_ if you want to talk to the developers.
 
-* We try to stay organized with `Theano's Trac <trac/>`__ 
+* We try to stay organized with `Theano's Trac <http://trac-hg.assembla.com/theano/report/1>`__ 
 
 * Come visit us in Montreal!  Most of the developers are students in the LISA_ group at the `University of Montreal`_.
 
@@ -68,8 +69,6 @@ Community
    LICENSE
 
 
-
-
 .. _theano-dev: http://groups.google.com/group/theano-dev
 .. _theano-users: http://groups.google.com/group/theano-users
 .. _tickets: http://pylearn.org/theano/trac/query?status=accepted&status=assigned&status=new&status=reopened&group=milestone&max=200&col=id&col=summary&col=status&col=owner&col=type&col=priority&col=component&col=time&report=9&order=priority

doc/install.txt

@@ -278,8 +278,11 @@ but this has not been tested yet.
   ``export PYTHONPATH=PYTHONPATH:$HOME/Theano``.
 
 - Please note that at this time, some tests (launched using ``nosetests``) are
-  still failing under Windows.
-  We are working on fixing them.
+  still failing under Windows: we are working on fixing them.
+  It may also happen that many tests may fail while running the test-suite,
+  due to insufficient memory resources: one workaround is to run nosetests
+  multiple times under individual subdirectories.
+  
 
 Generating the documentation
 ----------------------------

doc/internal/dev_start_guide.txt

@@ -119,9 +119,6 @@ to your ``Theano`` folder and execute the following command:
 
     hg pull -u
 
-You may also download the latest source directly as a gzip'd tar file:
-`<http://pylearn.org/hg/Theano/archive/tip.tar.gz>`__.
-
 Nightly test
 ============
 

doc/library/tensor/basic.txt

@@ -331,6 +331,8 @@ Indexing
 
 Basic indexing.
 
+    Mirrors numpy's `basic indexing  <http://docs.scipy.org/doc/numpy/reference/arrays.indexing.html>`_. Read that page first.
+
 Advanced indexing.
 
 .. _libdoc_tensor_elementwise:

doc/links.txt

@@ -40,10 +40,10 @@ This is a sort of memo for developers and would-be developers.
 .. _mercurial: http://www.selenic.com/mercurial/wiki/
 .. _nosetests: http://somethingaboutorange.com/mrl/projects/nose/
 .. _numpy: http://numpy.scipy.org/
-.. _python: http://www.python.or
+.. _python: http://www.python.org
 .. _scipy: http://scipy.org/
 
-.. _autodiff: http://autodiff.org
+.. _autodiff: http://www.autodiff.org
 .. _boost.python: http://www.boost.org/doc/libs/1_38_0/libs/python/doc/index.html
 .. _cython: http://www.cython.org/
 .. _liboil: http://liboil.freedesktop.org/wiki/

doc/tutorial/symbolic_graphs.txt

@@ -105,7 +105,7 @@ how to compute the gradient of the node's outputs with respect to its
 inputs. Note that if an :ref:`op` does not provide this information, 
 it is assumed that the gradient does not defined.
 Using the 
-`chain rule <http://en.wikipedia.org/wiki/Chain_rile>`_ 
+`chain rule <http://en.wikipedia.org/wiki/Chain_rule>`_ 
 these gradients can be composed in order to obtain the expression of the 
 gradient of the graph's output with respect to the graph's inputs .
 

theano/sandbox/cuda/__init__.py

 import os, sys
 from theano.gof.compiledir import get_compiledir
 from theano.compile import optdb
+import theano.config as config
 
 import logging, copy
 _logger_name = 'theano_cuda_ndarray'
@@ -15,8 +16,34 @@ def debug(*msg):
     _logger.debug(_logger_name+'DEBUG: '+' '.join(str(m) for m in msg))
 
 
-#compile type_support.cu
-#this need that nvcc(part of cuda) is installed
+# Compile type_support.cu
+# This need that nvcc (part of cuda) is installed. If it is not, a warning is
+# printed and this module will not be working properly (we set `enable_cuda`
+# to False).
+
+# This variable is True by default, and set to False if something goes wrong
+# when trying to initialize cuda.
+enable_cuda = True
+
+# Global variable to avoid displaying the same warning multiple times.
+cuda_warning_is_displayed = False
+
+# Code factorized within a function so that it may be called from multiple
+# places (which is not currently the case, but may be useful in the future).
+def set_cuda_disabled():
+    """Function used to disable cuda.
+
+    A warning is displayed, so that the user is aware that cuda-based code is
+    not going to work.
+    Note that there is no point calling this function from outside of
+    `cuda.__init__`, since it has no effect once the module is loaded.
+    """
+    global enable_cuda, cuda_warning_is_displayed
+    enable_cuda = False
+    if not cuda_warning_is_displayed:
+        cuda_warning_is_displayed = True
+        warning('Cuda is disabled, cuda-based code will thus not be '
+                'working properly')
 
 old_file = os.path.join(os.path.split(__file__)[0],'type_support.so')
 if os.path.exists(old_file):
@@ -30,55 +57,58 @@ except ImportError:
 
     import nvcc_compiler
 
-    print __file__
+    if not nvcc_compiler.is_nvcc_available():
+        set_cuda_disabled()
 
-    cuda_path=os.path.split(old_file)[0]
-    code = open(os.path.join(cuda_path, "type_support.cu")).read()
+    if enable_cuda:
+        print __file__
 
-    loc = os.path.join(get_compiledir(),'type_support')
-    if not os.path.exists(loc):
-        os.makedirs(loc)
+        cuda_path=os.path.split(old_file)[0]
+        code = open(os.path.join(cuda_path, "type_support.cu")).read()
+
+        loc = os.path.join(get_compiledir(),'type_support')
+        if not os.path.exists(loc):
+            os.makedirs(loc)
  
-    CUDA_NDARRAY=os.getenv('CUDA_NDARRAY')
-    include_dirs=[]
-    lib_dirs=[]
+        CUDA_NDARRAY=os.getenv('CUDA_NDARRAY')
+        include_dirs=[]
+        lib_dirs=[]
     
-    if CUDA_NDARRAY:
-        include_dirs.append(CUDA_NDARRAY)
-        lib_dirs.append(CUDA_NDARRAY)
-    else:
-        import theano.sandbox
-        path = os.path.split(os.path.split(os.path.split(theano.sandbox.__file__)[0])[0])[0]
-        path2 = os.path.join(path,'cuda_ndarray')
-        if os.path.isdir(path2):
-            include_dirs.append(path2)
-            lib_dirs.append(path2)
+        if CUDA_NDARRAY:
+            include_dirs.append(CUDA_NDARRAY)
+            lib_dirs.append(CUDA_NDARRAY)
         else:
-            path = os.path.split(path)[0]
+            import theano.sandbox
+            path = os.path.split(os.path.split(os.path.split(theano.sandbox.__file__)[0])[0])[0]
             path2 = os.path.join(path,'cuda_ndarray')
-            include_dirs.append(path2)
-            lib_dirs.append(path2)
+            if os.path.isdir(path2):
+                include_dirs.append(path2)
+                lib_dirs.append(path2)
+            else:
+                path = os.path.split(path)[0]
+                path2 = os.path.join(path,'cuda_ndarray')
+                include_dirs.append(path2)
+                lib_dirs.append(path2)
+
+        nvcc_compiler.nvcc_module_compile_str('type_support', code, location = loc, include_dirs=include_dirs, lib_dirs=lib_dirs, libs=['cuda_ndarray'])
+
+        from type_support.type_support import *
+
+
+if enable_cuda:
+    from theano.sandbox.cuda.type import CudaNdarrayType
+    from theano.sandbox.cuda.var import (CudaNdarrayVariable,
+            CudaNdarrayConstant,
+            CudaNdarraySharedVariable,
+            shared_constructor)
+
+    import basic_ops
+    from basic_ops import (GpuFromHost, HostFromGpu, GpuElemwise, 
+            GpuDimShuffle, GpuSum, GpuReshape, 
+            GpuSubtensor, GpuIncSubtensor, GpuFlatten, GpuShape)
+    import opt
+    import cuda_ndarray
 
-    nvcc_compiler.nvcc_module_compile_str('type_support', code, location = loc, include_dirs=include_dirs, lib_dirs=lib_dirs, libs=['cuda_ndarray'])
-
-    from type_support.type_support import *
-
-
-
-from theano.sandbox.cuda.type import CudaNdarrayType
-from theano.sandbox.cuda.var import (CudaNdarrayVariable,
-    CudaNdarrayConstant,
-    CudaNdarraySharedVariable,
-    shared_constructor)
-
-import basic_ops
-from basic_ops import (GpuFromHost, HostFromGpu, GpuElemwise, 
-                       GpuDimShuffle, GpuSum, GpuReshape, 
-                       GpuSubtensor, GpuIncSubtensor, GpuFlatten, GpuShape)
-import opt
-import cuda_ndarray
-
-import theano.config as config
 
 def use(device=config.THEANO_GPU):
     if use.device_number is None:

theano/sandbox/cuda/nvcc_compiler.py

@@ -19,6 +19,15 @@ def debug(*args):
     #sys.stderr.write('DEBUG:'+ ' '.join(str(a) for a in args)+'\n')
     _logger.debug("DEBUG: "+' '.join(str(a) for a in args))
 
+def is_nvcc_available():
+    """Return True iff the nvcc compiler is found."""
+    try:
+        subprocess.call(['nvcc', '--version'], stdout=subprocess.PIPE,
+                stderr=subprocess.PIPE)
+        return True
+    except:
+        return False
+
 def nvcc_module_compile_str(module_name, src_code, location=None, include_dirs=[], lib_dirs=[], libs=[],
         preargs=[]):
     """

theano/tensor/opt.py

@@ -346,7 +346,7 @@ def local_IncSubtensor_serialize(node):
 
     #
     #  add(x, incsubtensor(b, c), incsubtensor(b, d))
-    #  -> incsubtensor(incsubtensor(add(x,b), c), d)
+    #  -> incsubtensor(incsubtensor(add(x,b,b), c), d)
     
     """
     def movable(i):
@@ -354,7 +354,8 @@ def local_IncSubtensor_serialize(node):
         return i.owner \
                 and isinstance(i.owner.op, T.IncSubtensor) \
                 and i.type == o_type \
-                and len(i.clients) == 1
+                and len(i.clients) == 1 \
+                and not i.owner.op.set_instead_of_inc
 
     if node.op == T.add:
         o_type = node.outputs[0].type
@@ -383,7 +384,8 @@ def local_IncSubtensor_serialize(node):
 @gof.local_optimizer([None])
 def local_inplace_setsubtensor(node):
     if isinstance(node.op, T.IncSubtensor) and not node.op.inplace:
-        new_op = T.IncSubtensor(node.op.idx_list, inplace=True)
+        new_op = T.IncSubtensor(node.op.idx_list, inplace=True, \
+                        set_instead_of_inc=node.op.set_instead_of_inc)
         new_node = new_op(*node.inputs)
         return [new_node]
     return False

theano/tensor/raw_random.py

@@ -309,7 +309,9 @@ def permutation_helper(random_state, n, shape):
     """
     # n should be a 0-dimension array
     assert n.shape == ()
-    n = n.item()
+    # Note that it is important to convert `n` into an integer, because if it
+    # is a long, the numpy permutation function will crash on Windows.
+    n = int(n.item())
 
     out_shape = list(shape)
     out_shape.append(n)

theano/tensor/sharedvar.py

@@ -35,7 +35,7 @@ class ScalarSharedVariable(SharedVariable, _tensor_py_operators):
 
 @shared_constructor
 def scalar_constructor(value, name=None, strict=False, dtype=None):
-    """SharedVariable constructor for scalar values. Defaults to int64 or float64. 
+    """SharedVariable constructor for scalar values. Default: int64 or float64. 
 
     :note: We implement this using 0-d tensors for now.
     
@@ -50,12 +50,14 @@ def scalar_constructor(value, name=None, strict=False, dtype=None):
         else:
             dtype = type(value).__name__
 
-    type = TensorType(dtype=dtype, broadcastable=[])
+    tensor_type = TensorType(dtype=dtype, broadcastable=[])
 
     try:
-        # don't pass the dtype to asarray because we want this to fail if strict is True and the
-        # types do not match
-        rval = ScalarSharedVariable(type=type, value=numpy.asarray(value), name=name, strict=strict)
+        # Do not pass the dtype to asarray because we want this to fail if
+        # strict is True and the types do not match.
+        rval = ScalarSharedVariable(type=tensor_type,
+                value=numpy.asarray(value),
+                name=name, strict=strict)
         return rval
     except:
         traceback.print_exc()

theano/tensor/tests/test_randomstreams.py

@@ -277,12 +277,12 @@ class T_RandomStreams(unittest.TestCase):
         assert numpy.all(fn_val1 == numpy_val1)
 
     def test_shuffle_row_elements(self):
-        """Test that RandomStreams.shuffle_row_elements generates the right results"""
+        """Ensure RandomStreams.shuffle_row_elements generates right results"""
         # Check over two calls to see if the random state is correctly updated.
-
-        # On matrices, for each row, the elements of that row should be shuffled.
-        # Note that this differs from numpy.random.shuffle, where all the elements
-        # of the matrix are shuffled.
+        # On matrices, for each row, the elements of that row should be
+        # shuffled.
+        # Note that this differs from numpy.random.shuffle, where all the
+        # elements of the matrix are shuffled.
         mm = Module()
         mm.random = RandomStreams(234)
         m_input = tensor.dmatrix()