Merge pull request #4370 from nouiz/small

Theano.pyproj

-<?xml version="1.0" encoding="utf-8"?>
+<?xml version="1.0" encoding="utf-8"?>
 <Project DefaultTargets="Build" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
   <PropertyGroup>
     <Configuration Condition=" '$(Configuration)' == '' ">Debug</Configuration>
@@ -134,14 +134,12 @@
     <Compile Include="theano\sandbox\linalg\__init__.py" />
     <Compile Include="theano\sandbox\minimal.py" />
     <Compile Include="theano\sandbox\multinomial.py" />
-    <Compile Include="theano\sandbox\neighbourhoods.py" />
     <Compile Include="theano\sandbox\neighbours.py" />
     <Compile Include="theano\sandbox\rng_mrg.py" />
     <Compile Include="theano\sandbox\softsign.py" />
     <Compile Include="theano\sandbox\solve.py" />
     <Compile Include="theano\sandbox\symbolic_module.py" />
     <Compile Include="theano\sandbox\test_multinomial.py" />
-    <Compile Include="theano\sandbox\test_neighbourhoods.py" />
     <Compile Include="theano\sandbox\test_neighbours.py" />
     <Compile Include="theano\sandbox\test_rng_mrg.py" />
     <Compile Include="theano\sandbox\test_theano_object.py" />

doc/library/compile/mode.txt

@@ -22,6 +22,7 @@ Theano defines the following modes by name:
 - ``'FAST_RUN'``: Apply all optimizations, and use C implementations where possible.
 - ``'DebugMode'``: A mode for debugging. See :ref:`DebugMode <debugmode>` for details.
 - ``'ProfileMode'``: Deprecated, use the Theano flag :attr:`config.profile`.
+- ``'NanGuardMode``: :ref:`Nan detector <nanguardmode>`
 - ``'DEBUG_MODE'``: Deprecated. Use the string DebugMode.
 - ``'PROFILE_MODE'``: Deprecated, use the Theano flag :attr:`config.profile`.
 

doc/library/sandbox/cuda/dnn.txt

@@ -46,9 +46,9 @@ get an error when cuDNN can not be used with them, use this flag:
 
 .. note::
 
-   cuDNN v3 has now been released. cuDNN v2 remains supported but cuDNN v3 is
-   faster and offers many more options. We recommend that everybody update to
-   v3.
+   cuDNN v5rc is supported in Theano master version. So it dropped cuDNN v3 support.
+   Theano 0.8.0 and 0.8.1 support only cuDNN v3 and v4.
+   Theano 0.8.2 will support only v4 and v5.
 
 .. note::
 

doc/library/sandbox/gpuarray/dnn.txt

@@ -43,9 +43,9 @@ To get an error if Theano can not use cuDNN, use this Theano flag:
 
 .. note::
 
-   cuDNN v3 has now been released. cuDNN v2 remains supported but cuDNN v3 is
-   faster and offers many more options. We recommend that everybody update to
-   v3.
+   cuDNN v5rc is supported in Theano master version. So it dropped cuDNN v3 support.
+   Theano 0.8.0 and 0.8.1 support only cuDNN v3 and v4.
+   Theano 0.8.2 will support only v4 and v5.
 
 .. note::
 

doc/tutorial/modes.txt

@@ -142,7 +142,7 @@ Theano defines the following modes by name:
 - ``'DebugMode'``: Verify the correctness of all optimizations, and compare C and Python
     implementations. This mode can take much longer than the other modes, but can identify
     several kinds of problems.
-- ``'ProfileMode'`` (deprecated): Same optimization as FAST_RUN, but print some profiling information.
+- ``'NanGuardMode'``: Same optimization as FAST_RUN, but :ref:`check if a node generate nans. <nanguardmode>`
 
 The default mode is typically ``FAST_RUN``, but it can be controlled via
 the configuration variable :attr:`config.mode`,
@@ -155,7 +155,6 @@ short name        Full constructor
 ``FAST_COMPILE``  ``compile.mode.Mode(linker='py', optimizer='fast_compile')``    Python implementations only, quick and cheap graph transformations
 ``FAST_RUN``      ``compile.mode.Mode(linker='cvm', optimizer='fast_run')``       C implementations where available, all available graph transformations.
 ``DebugMode``     ``compile.debugmode.DebugMode()``                               Both implementations where available, all available graph transformations.
-``ProfileMode``   ``compile.profilemode.ProfileMode()``                           Deprecated. C implementations where available, all available graph transformations, print profile information.
 ================= =============================================================== ===============================================================================
 
 .. Note::
@@ -169,8 +168,8 @@ Linkers
 =======
 
 A mode is composed of 2 things: an optimizer and a linker. Some modes,
-like ``ProfileMode`` and ``DebugMode``, add logic around the optimizer and
-linker. ``ProfileMode`` and ``DebugMode`` use their own linker.
+like ``NanGuardMode`` and ``DebugMode``, add logic around the optimizer and
+linker. ``NanGuardMode`` and ``DebugMode`` use their own linker.
 
 You can select which linker to use with the Theano flag :attr:`config.linker`.
 Here is a table to compare the different linkers.
@@ -184,7 +183,7 @@ c|py [#cpy1]_  yes        yes                "+++"      Try C code. If none exis
 c|py_nogc      no         yes                "++"       As c|py, but without gc
 c              no         yes                "+"        Use only C code (if none available for an op, raise an error)
 py             yes        yes                "+++"      Use only Python code
-ProfileMode    no         no                 "++++"     (Deprecated) Compute some extra profiling info
+NanGuardMode    no         no                 "++++"    Check if nodes generate NaN
 DebugMode      no         yes                VERY HIGH  Make many checks on what Theano computes
 =============  =========  =================  =========  ===
 
@@ -259,123 +258,3 @@ ProfileMode
 .. note::
 
     ProfileMode is deprecated. Use :attr:`config.profile` instead.
-
-
-Besides checking for errors, another important task is to profile your
-code. For this Theano uses a special mode called ProfileMode which has
-to be passed as an argument to :func:`theano.function <function.function>`.
-Using the ProfileMode is a three-step process.
-
-.. note::
-
-    To switch the default accordingly, set the Theano flag
-    :attr:`config.mode` to ProfileMode.  In that case, when the Python
-    process exits, it will automatically print the profiling
-    information on the standard output.
-
-    The memory profile of the output of each ``apply`` node can be enabled with the
-    Theano flag :attr:`config.ProfileMode.profile_memory`.
-
-For more detail, see :ref:`ProfileMode <profilemode>` in the library.
-
-Creating a ProfileMode Instance
--------------------------------
-
-First create a ProfileMode instance:
-
->>> from theano import ProfileMode
->>> profmode = theano.ProfileMode(optimizer='fast_run', linker=theano.gof.OpWiseCLinker())
-
-The ProfileMode constructor takes as input an optimizer and a
-linker. Which optimizer and linker to use will depend on the
-application. For example, a user wanting to profile the Python
-implementation only, should use the gof.PerformLinker (or "py" for
-short). On the other hand, a user wanting to profile his graph using C
-implementations wherever possible should use the ``gof.OpWiseCLinker``
-(or "c|py"). For testing the speed of your code we would recommend
-using the ``fast_run`` optimizer and the ``gof.OpWiseCLinker`` linker.
-
-Compiling your Graph with ProfileMode
--------------------------------------
-
-Once the ProfileMode instance is created, simply compile your graph as you
-would normally, by specifying the mode parameter.
-
->>> v1, v2 = T.vectors(2)
->>> o = v1 + v2
->>> f = theano.function([v1,v2],[o], mode=profmode)
-
-Retrieving Timing Information
------------------------------
-
-Once your graph is compiled, simply run the program or operation you wish to
-profile, then call ``profmode.print_summary()``. This will provide you with
-the desired timing information, indicating where your graph is spending most
-of its time. This is best shown through an example. Let's use our logistic
-regression example.
-
-Compiling the module with ``ProfileMode`` and calling ``profmode.print_summary()``
-generates the following output:
-
-.. code-block:: python
-
-    """
-    ProfileMode.print_summary()
-    ---------------------------
-
-    local_time 0.0749197006226 (Time spent running thunks)
-    Apply-wise summary: <fraction of local_time spent at this position> (<Apply position>, <Apply Op name>)
-            0.069   15      _dot22
-            0.064   1       _dot22
-            0.053   0       InplaceDimShuffle{x,0}
-            0.049   2       InplaceDimShuffle{1,0}
-            0.049   10      mul
-            0.049   6       Elemwise{ScalarSigmoid{output_types_preference=<theano.scalar.basic.transfer_type object at 0x171e650>}}[(0, 0)]
-            0.049   3       InplaceDimShuffle{x}
-            0.049   4       InplaceDimShuffle{x,x}
-            0.048   14      Sum{0}
-            0.047   7       sub
-            0.046   17      mul
-            0.045   9       sqr
-            0.045   8       Elemwise{sub}
-            0.045   16      Sum
-            0.044   18      mul
-       ... (remaining 6 Apply instances account for 0.25 of the runtime)
-    Op-wise summary: <fraction of local_time spent on this kind of Op> <Op name>
-            0.139   * mul
-            0.134   * _dot22
-            0.092   * sub
-            0.085   * Elemwise{Sub{output_types_preference=<theano.scalar.basic.transfer_type object at 0x1779f10>}}[(0, 0)]
-            0.053   * InplaceDimShuffle{x,0}
-            0.049   * InplaceDimShuffle{1,0}
-            0.049   * Elemwise{ScalarSigmoid{output_types_preference=<theano.scalar.basic.transfer_type object at 0x171e650>}}[(0, 0)]
-            0.049   * InplaceDimShuffle{x}
-            0.049   * InplaceDimShuffle{x,x}
-            0.048   * Sum{0}
-            0.045   * sqr
-            0.045   * Sum
-            0.043   * Sum{1}
-            0.042   * Elemwise{Mul{output_types_preference=<theano.scalar.basic.transfer_type object at 0x17a0f50>}}[(0, 1)]
-            0.041   * Elemwise{Add{output_types_preference=<theano.scalar.basic.transfer_type object at 0x1736a50>}}[(0, 0)]
-            0.039   * Elemwise{Second{output_types_preference=<theano.scalar.basic.transfer_type object at 0x1736d90>}}[(0, 1)]
-       ... (remaining 0 Ops account for 0.00 of the runtime)
-    (*) Op is running a c implementation
-
-    """
-
-
-This output has two components. In the first section called
-*Apply-wise summary*, timing information is provided for the worst
-offending ``Apply`` nodes. This corresponds to individual op applications
-within your graph which took longest to execute (so if you use
-``dot`` twice, you will see two entries there). In the second portion,
-the *Op-wise summary*, the execution time of all ``Apply`` nodes executing
-the same op are grouped together and the total execution time per op
-is shown (so if you use ``dot`` twice, you will see only one entry
-there corresponding to the sum of the time spent in each of them).
-Finally, notice that the ``ProfileMode`` also shows which ops were running a C
-implementation.
-
-
-For more detail, see :ref:`ProfileMode<profilemode>` in the library.
-

setup.py

@@ -52,9 +52,9 @@ AUTHOR              = "LISA laboratory, University of Montreal"
 AUTHOR_EMAIL        = "theano-dev@googlegroups.com"
 PLATFORMS           = ["Windows", "Linux", "Solaris", "Mac OS-X", "Unix"]
 MAJOR               = 0
-MINOR               = 8
+MINOR               = 9
 MICRO               = 0
-SUFFIX              = ""  # Should be blank except for rc's, betas, etc.
+SUFFIX              = "dev0"  # Should be blank except for rc's, betas, etc.
 ISRELEASED          = False
 
 VERSION             = '%d.%d.%d%s' % (MAJOR, MINOR, MICRO, SUFFIX)

theano/gof/fg.py

@@ -49,8 +49,19 @@ class MissingInputError(Exception):
     A symbolic input needed to compute the outputs is missing.
 
     """
-
-    pass
+    def __init__(self, *args, **kwargs):
+        if kwargs:
+            # The call to list is needed for Python 3
+            assert list(kwargs.keys()) == ["variable"]
+            tr = getattr(list(kwargs.values())[0].tag, 'trace', [])
+            if type(tr) is list and len(tr) > 0:
+                sio = StringIO()
+                print("\nBacktrace when the variable is created:", file=sio)
+                for subtr in list(kwargs.values())[0].tag.trace:
+                    traceback.print_list(subtr, sio)
+                args = args + (str(sio.getvalue()),)
+        s = '\n'.join(args)  # Needed to have the new line print correctly
+        Exception.__init__(self, s)
 
 
 class FunctionGraph(utils.object2):
@@ -364,7 +375,7 @@ class FunctionGraph(utils.object2):
             if isinstance(variable.type, NullType):
                 raise TypeError("Computation graph contains a NaN. " +
                                 variable.type.why_null)
-            raise MissingInputError("Undeclared input", variable)
+            raise MissingInputError("Undeclared input", variable=variable)
         if not getattr(variable, 'fgraph', None) is self:
             self.__setup_r__(variable)
         self.variables.add(variable)
@@ -392,78 +403,6 @@ class FunctionGraph(utils.object2):
                     if (r.owner is None and
                             not isinstance(r, graph.Constant) and
                             r not in self.inputs):
-                        # Verbose error message
-                        # Show a complete chain of variables from the missing input to an output
-                        if config.exception_verbosity == 'high':
-
-                            def find_path_to(output_var, input_var):
-                                """
-                                Returns a list of each variable on a (not
-                                necessarily unique) path from input_var to
-                                output_var, where each variable in the list has
-                                the preceding variable as one of its inputs.
-                                Returns None if no path exists.
-
-                                """
-                                # If output and input are the same we have a singleton path
-                                if output_var is input_var:
-                                    return [output_var]
-
-                                # If output has no inputs then there is no path
-                                owner = output_var.owner
-
-                                if owner is None:
-                                    return None
-
-                                # If input_var is an input to the output node, there is a
-                                # simple two element path
-                                inputs = owner.inputs
-
-                                if input_var in inputs:
-                                    return [input_var, output_var]
-
-                                # Otherwise we must recurse by searching for a path to one
-                                # of our inputs, then appending the output to that path
-                                for ipt in inputs:
-                                    path = find_path_to(ipt, input_var)
-
-                                    if path is not None:
-                                        path.append(output_var)
-
-                                        return path
-
-                                # Since none of the above methods returned a path, there is none
-                                return None
-
-                            # Try different outputs until we find one that has a path to the missing input
-                            for output in self.outputs:
-                                path = find_path_to(output, r)
-
-                                if path is not None:
-                                    break
-
-                            # if there is no path then r isn't really a graph input so we shouldn't be running error
-                            # handler code in the first place
-                            assert path is not None
-                            tr = getattr(r.tag, 'trace', [])
-                            detailed_err_msg = ""
-                            if type(tr) is list and len(tr) > 0:
-                                detailed_err_msg += "\nBacktrace when the variable is created:\n"
-
-                                # Print separate message for each element in
-                                # the list of batcktraces
-                                sio = StringIO()
-                                for subtr in tr:
-                                    traceback.print_list(subtr, sio)
-                                detailed_err_msg += str(sio.getvalue())
-                            raise MissingInputError(
-                                'A variable that is an input to the graph was '
-                                'neither provided as an input to the function '
-                                'nor given a value. A chain of variables '
-                                'leading from this input to an output is %s. '
-                                'This chain may not be unique' % str(path) +
-                                detailed_err_msg)
-
                         # Standard error message
                         raise MissingInputError((
                             "An input of the graph, used to compute %s, "
@@ -471,7 +410,7 @@ class FunctionGraph(utils.object2):
                             "Use the Theano flag exception_verbosity='high',"
                             "for more information on this error."
                             % str(node)),
-                            r)
+                            variable=r)
 
         for node in new_nodes:
             assert node not in self.apply_nodes

theano/sandbox/tests/test_neighbourhoods.py

-from __future__ import absolute_import, print_function, division
-#!/usr/bin/python
-
-import theano
-import numpy
-
-import theano.tensor as T
-
-from theano.sandbox.neighbourhoods import *
-
-'''
-def test_imgFromNeigh_noborder_1d():
-    x = T.dtensor3()
-
-    a = numpy.arange(2*2*6).reshape((2,2,6))
-
-    neighs = NeighbourhoodsFromImages(2, (3,))(x)
-
-    f = theano.function([x], neighs)
-
-    z = f(a)
-    
-    cmp = numpy.asarray([[[[  0.,   1.,   2.],
-        [  3.,   4.,   5.]],
-        [[  6.,   7.,   8.],
-        [  9.,  10.,  11.]]],
-        [[[ 12.,  13.,  14.],
-        [ 15.,  16.,  17.]],
-        [[ 18.,  19.,  20.],
-        [ 21.,  22.,  23.]]]])
-
-    assert numpy.allclose(z, cmp)
-
-    x2 = T.dtensor4()
-
-    imgs = ImagesFromNeighbourhoods(2, (3,))(x2)
-
-    f2 = theano.function([x2], imgs)
-    z2 = f2(cmp)
-
-    assert numpy.allclose(z2, a)
-   
-def test_imgFromNeigh_1d_stridesmaller():
-    x = T.dtensor3()
-
-    a = numpy.arange(2*4).reshape((2,4))
-
-    #neighs = NeighbourhoodsFromImages(1, (3,), strides=(1,), ignore_border=False)(x)
-
-    cmp = numpy.asarray([[[0.,1.,2.],[1.,2.,3.],[2.,3.,0.],[3.,0.,0.]],\
-                [[4.,5.,6.],[5.,6.,7.],[6.,7.,0.],[7.,0.,0.]]])
-
-    images = ImagesFromNeighbourhoods(1, (3,), strides=(1,), ignore_border=False)(x)
-
-    f = theano.function([x], images)
-
-    aprime = f(cmp)
-
-    should_be = [[0.,  1.,  2.,  3.,  0.,  0.], [ 4.,  5.,  6.,  7.,  0.,  0.]]
-
-    assert numpy.allclose(aprime, should_be)
-
-def test_neighFromImg_1d():
-    x = T.dtensor3()
-
-    a = numpy.arange(2*2*6).reshape((2,2,6))
-
-    neighs = NeighbourhoodsFromImages(2, (3,))(x)
-
-    f = theano.function([x], neighs)
-
-    z = f(a)
-    
-    cmp = numpy.asarray([[[[  0.,   1.,   2.],
-        [  3.,   4.,   5.]],
-        [[  6.,   7.,   8.],
-        [  9.,  10.,  11.]]],
-        [[[ 12.,  13.,  14.],
-        [ 15.,  16.,  17.]],
-        [[ 18.,  19.,  20.],
-        [ 21.,  22.,  23.]]]])
-
-    assert numpy.allclose(z, cmp)
-
-def test_neighFromImg_1d_ignoreborder():
-    x = T.dtensor3()
-
-    a = numpy.arange(1*2*7).reshape((1,2,7))
-
-    neighs = NeighbourhoodsFromImages(2, (3,), ignore_border=True)(x)
-
-    f = theano.function([x], neighs)
-
-    z = f(a)
-
-    cmp = numpy.asarray([[[[  0.,   1.,   2.],
-        [  3.,   4.,   5.]],
-        [[  7.,   8.,  9.],
-        [  10.,  11.,  12.]]]])
-
-    assert numpy.allclose(z, cmp)
-
-def test_neighFromImg_1d_stridesmaller():
-    x = T.dmatrix()
-
-    a = numpy.arange(2*4).reshape((2,4))
-
-    neighs = NeighbourhoodsFromImages(1, (3,), strides=(1,), ignore_border=False)(x)
-
-    f = theano.function([x], neighs)
-
-    z = f(a)
-
-    cmp = numpy.asarray([[[0.,1.,2.],[1.,2.,3.],[2.,3.,0.],[3.,0.,0.]],\
-                [[4.,5.,6.],[5.,6.,7.],[6.,7.,0.],[7.,0.,0.]]])
-
-    assert numpy.allclose(z, cmp)
-
-def test_neighFromImg_1d_stridesbigger():
-    x = T.dmatrix()
-
-    a = numpy.arange(2*4).reshape((2,4))
-
-    neighs = NeighbourhoodsFromImages(1, (2,), strides=(3,), ignore_border=False)(x)
-
-    f = theano.function([x], neighs)
-
-    z = f(a)
-
-    cmp = numpy.asarray([[[0.,1.],[3.,0.]],\
-                [[4.,5.],[7.,0.]]])
-
-    assert numpy.allclose(z, cmp)
-
-def test_neighFromImg_2d():
-    x = T.dtensor3()
-
-    a = numpy.arange(2*5*3).reshape((2,5,3))
-
-    neighs = NeighbourhoodsFromImages(1, (2,2), ignore_border=False)(x)
-
-    f = theano.function([x], neighs)
-
-    z = f(a)
-
-    cmp = numpy.asarray([[[[  0.,   1.,   3.,   4.,],
-           [  2.,   0.,   5.,   0.,]],
-          [[  6.,   7.,   9.,  10.,],
-           [  8.,   0.,  11.,   0.,]],
-          [[ 12.,  13.,   0.,   0.,],
-           [ 14.,   0.,   0.,   0.,]]],
-         [[[ 15.,  16.,  18.,  19.,],
-           [ 17.,   0.,  20.,   0.,]],
-          [[ 21.,  22.,  24.,  25.,],
-           [ 23.,   0.,  26.,   0.,]],
-          [[ 27.,  28.,   0.,   0.,],
-           [ 29.,   0.,   0.,   0.,]]]])
-
-    assert numpy.allclose(z, cmp)
-
-
-
-if __name__ == '__main__':
-
-    numpy.set_printoptions(threshold=numpy.nan)
-    test_neighFromImg_1d()
-    test_neighFromImg_1d_ignoreborder()
-    test_neighFromImg_1d_stridesmaller()
-    test_neighFromImg_1d_stridesbigger()
-    test_neighFromImg_2d()
-    test_imgFromNeigh_noborder_1d()
-    test_imgFromNeigh_1d_stridesmaller()
-'''
-

theano/tensor/nnet/conv.py

@@ -129,7 +129,8 @@ def conv2d(input, filters, image_shape=None, filter_shape=None,
 
     if image_shape and filter_shape:
         try:
-            assert image_shape[1] == filter_shape[1]
+            if image_shape[1] is not None and filter_shape[1] is not None:
+                assert image_shape[1] == filter_shape[1]
         except Exception:
             print('image ', image_shape, ' filters ', filter_shape)
             raise

theano/tests/test_flake8.py

@@ -89,7 +89,6 @@ whitelist_flake8 = [
     "sandbox/__init__.py",
     "sandbox/tests/test_theano_object.py",
     "sandbox/tests/test_scan.py",
-    "sandbox/tests/test_neighbourhoods.py",
     "sandbox/tests/__init__.py",
     "sandbox/cuda/var.py",
     "sandbox/cuda/GpuConvGrad3D.py",