Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into hsigmoid_gpu

paddle/operators/conv_transpose_op.cc

@@ -74,12 +74,12 @@ Conv2DTransposeOpMaker::Conv2DTransposeOpMaker(
             "The format of output tensor is also NCHW.");
   AddAttr<std::vector<int>>(
       "strides",
-      "(vector<int> defalut:{1, 1}), the strides(h_stride, w_stride) of "
+      "(vector<int> default:{1, 1}), the strides(h_stride, w_stride) of "
       "convolution transpose operator.")
       .SetDefault({1, 1});
   AddAttr<std::vector<int>>(
       "paddings",
-      "(vector<int> defalut:{0, 0}), the paddings(h_pad, w_pad) of convolution "
+      "(vector<int> default:{0, 0}), the paddings(h_pad, w_pad) of convolution "
       "transpose operator.")
       .SetDefault({0, 0});
   AddComment(R"DOC(
@@ -101,8 +101,8 @@ Example:
   Output:
        Output shape: (N, C_out, H_out, W_out)
   where
-       H_out = (H_in - 1) * strides[0] - 2 * paddings[0] + filter_size[0];
-       W_out = (W_in - 1) * strides[1] - 2 * paddings[1] + filter_size[1];
+       H_out = (H_in - 1) * strides[0] - 2 * paddings[0] + H_f;
+       W_out = (W_in - 1) * strides[1] - 2 * paddings[1] + W_f;
 )DOC");
 }
 
@@ -130,12 +130,12 @@ Conv3DTransposeOpMaker::Conv3DTransposeOpMaker(
             "the number of channels, D is the depth of the feature, H is the "
             "height of the feature, and W is the width of the feature.");
   AddAttr<std::vector<int>>("strides",
-                            "(vector<int> defalut:{1, 1, 1}), the "
+                            "(vector<int> default:{1, 1, 1}), the "
                             "strides{d_stride, h_stride, w_stride} of "
                             "convolution transpose operator.")
       .SetDefault({1, 1, 1});
   AddAttr<std::vector<int>>("paddings",
-                            "(vector<int> defalut:{0, 0, 0}), paddings(d_pad, "
+                            "(vector<int> default:{0, 0, 0}), paddings(d_pad, "
                             "h_pad, w_pad) of convolution transpose operator.")
       .SetDefault({0, 0, 0});
   AddComment(R"DOC(
@@ -158,9 +158,9 @@ Example:
   Output:
        Output shape: (N, C_out, D_out, H_out, W_out)
   where
-       D_out = (D_in - 1) * strides[0] - 2 * paddings[0] + filter_size[0];
-       H_out = (H_in - 1) * strides[1] - 2 * paddings[1] + filter_size[1];
-       W_out = (W_in - 1) * strides[2] - 2 * paddings[2] + filter_size[2];
+       D_out = (D_in - 1) * strides[0] - 2 * paddings[0] + D_f;
+       H_out = (H_in - 1) * strides[1] - 2 * paddings[1] + H_f;
+       W_out = (W_in - 1) * strides[2] - 2 * paddings[2] + W_f;
 )DOC");
 }
 

paddle/operators/detail/send_recv.proto

@@ -17,7 +17,7 @@ syntax = "proto3";
 package sendrecv;
 
 service SendRecvService {
-  // For parameter server round-robin like hashing, do not split tensors. 
+  // For parameter server round-robin like hashing, do not split tensors.
   // Send and recv only one tensor
   rpc SendVariable(VariableMessage) returns (VariableMessage) {}
 }
@@ -32,6 +32,4 @@ message VariableMessage {
   bytes serialized = 2;
 }
 
-message VoidMessage {
-
-}
\ No newline at end of file
+message VoidMessage {}
\ No newline at end of file

python/paddle/v2/fluid/evaluator.py

@@ -26,9 +26,9 @@ class Evaluator(object):
         name(str): The name of evaluator. such as, "accuracy". Used for generate 
             temporary variable name.
         main_program(Program, optional): The evaluator should be added to this 
-            main_program. Default g_main_program 
+            main_program. Default default_main_program()
         startup_program(Program, optional):The parameter should be added to this 
-            startup_program. Default g_startup_program
+            startup_program. Default default_startup_program()
             
     Attributes:
         states(list): The list of state variables. states will be reset to zero 

python/paddle/v2/fluid/executor.py

 import numpy as np
 from . import core
-from framework import Program, g_main_program
+from framework import Program, default_main_program
 
 __all__ = ['Executor', 'g_scope']
 
@@ -103,7 +103,7 @@ class Executor(object):
             fetch_list = []
 
         if program is None:
-            program = g_main_program
+            program = default_main_program()
 
         if not isinstance(program, Program):
             raise TypeError()

python/paddle/v2/fluid/framework.py

@@ -6,7 +6,7 @@ import proto.framework_pb2 as framework_pb2
 
 __all__ = [
     'Block', 'Variable', 'Program', 'Operator', 'default_startup_program',
-    'default_main_program', 'g_startup_program', 'g_main_program'
+    'default_main_program'
 ]
 
 
@@ -654,13 +654,13 @@ class Parameter(Variable):
 
 
 # program is a global instance.
-g_main_program = Program()
-g_startup_program = Program()
+_main_program_ = Program()
+_startup_program_ = Program()
 
 
 def default_startup_program():
-    return g_startup_program
+    return _startup_program_
 
 
 def default_main_program():
-    return g_main_program
+    return _main_program_

python/paddle/v2/fluid/io.py

 import os
 import cPickle as pickle
 
-from paddle.v2.fluid.framework import Program, Parameter, g_main_program, \
-    Variable
+from paddle.v2.fluid.framework import Program, Parameter, default_main_program, Variable
 
 __all__ = [
     'save_vars', 'save_params', 'save_persistables', 'load_vars', 'load_params',
@@ -46,7 +45,7 @@ def save_vars(executor, dirname, main_program=None, vars=None, predicate=None):
     """
     if vars is None:
         if main_program is None:
-            main_program = g_main_program
+            main_program = default_main_program()
         if not isinstance(main_program, Program):
             raise TypeError("program should be as Program type or None")
 
@@ -98,7 +97,7 @@ def load_vars(executor, dirname, main_program=None, vars=None, predicate=None):
     :param executor: executor that save variable
     :param dirname: directory path
     :param main_program: program. If vars is None, then filter all variables in this
-    program which fit `predicate`. Default g_program.
+    program which fit `predicate`. Default default_main_program().
     :param predicate: The Predicate describes a callable that returns a variable
     as a bool. If it returns true, the variables will be loaded.
     :param vars: variables need to be loaded. If specify vars, program &
@@ -107,7 +106,7 @@ def load_vars(executor, dirname, main_program=None, vars=None, predicate=None):
     """
     if vars is None:
         if main_program is None:
-            main_program = g_main_program
+            main_program = default_main_program()
         if not isinstance(main_program, Program):
             raise TypeError("program's type should be Program")
 
@@ -154,7 +153,7 @@ def load_persistables(executor, dirname, main_program=None):
 
 def get_inference_program(target_vars, main_program=None):
     if main_program is None:
-        main_program = g_main_program
+        main_program = default_main_program()
     if not isinstance(target_vars, list):
         target_vars = [target_vars]
 
@@ -177,12 +176,12 @@ def save_inference_model(dirname,
     :param target_vars: Variables from which we can get inference results.
     :param executor: executor that save inference model
     :param main_program: original program, which will be pruned to build the inference model.
-    Default g_main_program.
+            Default default_main_program().
 
     :return: None
     """
     if main_program is None:
-        main_program = g_main_program
+        main_program = default_main_program()
     if not isinstance(target_vars, list):
         target_vars = [target_vars]
 
@@ -272,10 +271,10 @@ def get_parameter_value_by_name(name, executor, program=None):
     :param executor: executor for retrieving the value
     :param name: the name of the parameter
     :param program: the program where the variable is found
-    Default g_main_program.
+            Default default_main_program().
     :return: the LoDTensor for the variable
     """
     if program is None:
-        program = g_main_program
+        program = default_main_program()
     var = program.global_block().var(name)
     return get_parameter_value(var, executor)

python/paddle/v2/fluid/layer_helper.py

 import copy
 import itertools
 
-from framework import Variable, g_main_program, \
-    g_startup_program, unique_name, dtype_is_floating
+from framework import Variable, default_main_program, default_startup_program, unique_name, dtype_is_floating
 from paddle.v2.fluid.initializer import Constant, Xavier
 
 
@@ -22,7 +21,7 @@ class LayerHelper(object):
     def main_program(self):
         prog = self.kwargs.get('main_program', None)
         if prog is None:
-            return g_main_program
+            return default_main_program()
         else:
             return prog
 
@@ -30,7 +29,7 @@ class LayerHelper(object):
     def startup_program(self):
         prog = self.kwargs.get('startup_program', None)
         if prog is None:
-            return g_startup_program
+            return default_startup_program()
         else:
             return prog
 

python/paddle/v2/fluid/layers.py

-from . import core
+import core
 import proto.framework_pb2 as framework_pb2
 from framework import OpProtoHolder, Variable, Program, Operator
-from initializer import Constant, Normal, Xavier
+from initializer import Constant, Normal, Xavier, Initializer
 from paddle.v2.fluid.layer_helper import LayerHelper, unique_name
 import re
 import cStringIO
@@ -1587,6 +1587,97 @@ def array_length(array, main_program=None):
     return tmp
 
 
+def conv2d_transpose(input,
+                     num_filters,
+                     output_size=None,
+                     filter_size=None,
+                     padding=None,
+                     stride=None,
+                     param_attr=None,
+                     param_initializer=None,
+                     main_program=None,
+                     startup_program=None):
+    """
+    The transpose of conv2d layer.
+    
+    This layer is also known as deconvolution layer.
+    
+    Args:
+        input(Variable): The input image with [N, C, H, W] format.
+        num_filters(int): The number of filter. It is as same as the output
+            image channel.
+        output_size(int|tuple|None): The output image size. If output size is a
+            tuple, it must contain two integers, (image_H, image_W). This 
+            parameter only works when filter_size is None.
+        filter_size(int|tuple|None): The filter size. If filter_size is a tuple,
+            it must contain two integers, (filter_size_H, filter_size_W).
+            Otherwise, the filter will be a square.  None if use output size to
+            calculate filter_size
+        padding(int|tuple): The padding size. If padding is a tuple, it must
+            contain two integers, (padding_H, padding_W). Otherwise, the 
+            padding_H = padding_W = padding.
+        stride(int|tuple): The stride size. If stride is a tuple, it must
+            contain two integers, (stride_H, stride_W). Otherwise, the
+            stride_H = stride_W = stride.
+        param_attr: Parameter Attribute.
+        param_initializer(Initializer): Parameter Initializer. Default is Xavier
+        main_program(Program): the main program
+        startup_program(Program): the startup program 
+
+    Returns:
+        Variable: Output image.
+    """
+    helper = LayerHelper("conv2d_transpose", **locals())
+    if not isinstance(input, Variable):
+        raise TypeError("Input of conv2d_transpose must be Variable")
+    input_channel = input.shape[1]
+
+    op_attr = dict()
+
+    if isinstance(padding, int):
+        op_attr['paddings'] = [padding, padding]
+    elif padding is not None:
+        op_attr['paddings'] = padding
+
+    if isinstance(stride, int):
+        op_attr['strides'] = stride
+    elif stride is not None:
+        op_attr['strides'] = stride
+
+    if filter_size is None:
+        if output_size is None:
+            raise ValueError("output_size must be set when filter_size is None")
+        if isinstance(output_size, int):
+            output_size = [output_size, output_size]
+
+        padding = op_attr.get('paddings', [0, 0])
+        stride = op_attr.get('strides', [1, 1])
+
+        h_in = input.shape[2]
+        w_in = input.shape[3]
+        filter_size_h = output_size[0] - (h_in - 1) * stride[0] + 2 * padding[0]
+        filter_size_w = output_size[1] - (w_in - 1) * stride[1] + 2 * padding[1]
+        filter_size = [filter_size_h, filter_size_w]
+    elif isinstance(filter_size, int):
+        filter_size = [filter_size, filter_size]
+
+    filter_shape = [input_channel, num_filters] + filter_size
+    img_filter = helper.create_parameter(
+        dtype=input.dtype,
+        shape=filter_shape,
+        attr=helper.param_attr,
+        initializer=param_initializer)
+
+    out = helper.create_tmp_variable(dtype=input.dtype)
+    helper.append_op(
+        type='conv2d_transpose',
+        inputs={'Input': [input],
+                'Filter': [img_filter]},
+        outputs={'Output': out},
+        attrs=op_attr)
+    return out
+
+
 class ConditionalBlockGuard(BlockGuard):
     def __init__(self, block):
         if not isinstance(block, ConditionalBlock):

python/paddle/v2/fluid/tests/test_array_read_write_op.py

@@ -3,7 +3,7 @@ import paddle.v2.fluid.core as core
 import paddle.v2.fluid.layers as layers
 from paddle.v2.fluid.executor import Executor
 from paddle.v2.fluid.backward import append_backward_ops
-from paddle.v2.fluid.framework import g_main_program
+from paddle.v2.fluid.framework import default_main_program
 import numpy
 
 
@@ -66,7 +66,7 @@ class TestArrayReadWrite(unittest.TestCase):
 
         append_backward_ops(total_sum_scaled)
 
-        g_vars = map(g_main_program.global_block().var,
+        g_vars = map(default_main_program().global_block().var,
                      [each_x.name + "@GRAD" for each_x in x])
         g_out = [
             item.sum()

python/paddle/v2/fluid/tests/test_conditional_block.py

 import unittest
 import paddle.v2.fluid.layers as layers
 import paddle.v2.fluid.core as core
-from paddle.v2.fluid.framework import g_startup_program, g_main_program
+from paddle.v2.fluid.framework import default_startup_program, default_main_program
 from paddle.v2.fluid.executor import Executor
 from paddle.v2.fluid.backward import append_backward_ops
 import numpy
@@ -19,7 +19,7 @@ class ConditionalBlock(unittest.TestCase):
 
         cpu = core.CPUPlace()
         exe = Executor(cpu)
-        exe.run(g_startup_program)
+        exe.run(default_startup_program())
 
         x = numpy.random.random(size=(10, 1)).astype('float32')
 
@@ -29,7 +29,9 @@ class ConditionalBlock(unittest.TestCase):
         append_backward_ops(loss=loss)
         outs = exe.run(
             feed={'X': x},
-            fetch_list=[g_main_program.block(0).var(data.name + "@GRAD")])[0]
+            fetch_list=[
+                default_main_program().block(0).var(data.name + "@GRAD")
+            ])[0]
         print outs
 
 

python/paddle/v2/fluid/tests/test_executor_and_mul.py

 import unittest
-from paddle.v2.fluid.layers import mul, data, sequence_pool
+
+import numpy
 import paddle.v2.fluid.core as core
+
 from paddle.v2.fluid.executor import Executor
-from paddle.v2.fluid.framework import g_main_program
-import numpy
+from paddle.v2.fluid.layers import mul, data
 
 
 class TestExecutor(unittest.TestCase):
@@ -19,10 +20,7 @@ class TestExecutor(unittest.TestCase):
         a_np = numpy.random.random((100, 784)).astype('float32')
         b_np = numpy.random.random((784, 100)).astype('float32')
         exe = Executor(place)
-        outs = exe.run(g_main_program,
-                       feed={'a': a_np,
-                             'b': b_np},
-                       fetch_list=[out])
+        outs = exe.run(feed={'a': a_np, 'b': b_np}, fetch_list=[out])
         out = outs[0]
         self.assertEqual((100, 100), out.shape)
         self.assertTrue(numpy.allclose(out, numpy.dot(a_np, b_np)))

python/paddle/v2/fluid/tests/test_layers.py

@@ -65,6 +65,15 @@ class TestBook(unittest.TestCase):
 
         print str(program)
 
+    def test_conv2d_transpose(self):
+        program = Program()
+        kwargs = {'main_program': program}
+        img = layers.data(
+            name='pixel', shape=[3, 2, 2], dtype='float32', **kwargs)
+        layers.conv2d_transpose(
+            input=img, num_filters=10, output_size=28, **kwargs)
+        print str(program)
+
     def test_recognize_digits_conv(self):
         program = Program()
 

python/paddle/v2/fluid/tests/test_lod_rank_table.py

 from paddle.v2.fluid.layers import lod_rank_table, data
 from paddle.v2.fluid.executor import Executor
-from paddle.v2.fluid.framework import g_main_program
 import paddle.v2.fluid.core as core
 import numpy
 import unittest
@@ -18,7 +17,7 @@ class TestLoDRankTable(unittest.TestCase):
         tensor = core.LoDTensor()
         tensor.set(numpy.random.random(size=(17, 100)), cpu)
         tensor.set_lod([[0, 1, 3], [0, 5, 6, 7], [0, 3, 4, 9, 10, 13, 16, 17]])
-        exe.run(g_main_program, scope=scope, feed={'x': tensor})
+        exe.run(scope=scope, feed={'x': tensor})
         var = scope.find_var(rank_table.name)
         table = var.get_lod_rank_table()
         self.assertEqual([(0, 5), (1, 1), (2, 1)], table.items())

python/paddle/v2/fluid/tests/test_operator_desc.py

 import unittest
-from paddle.v2.fluid.framework import Variable, Program, g_main_program
+
 import paddle.v2.fluid.core as core
 
+from paddle.v2.fluid.framework import Program, default_startup_program
+
+main_program = default_startup_program()
+
 
 class TestOperator(unittest.TestCase):
     def test_error_type(self):
-        block = g_main_program.create_block()
+        block = main_program.create_block()
         try:
             block.append_op()
             self.assertFail()

python/paddle/v2/fluid/tests/test_parameter.py

 import unittest
-from paddle.v2.fluid.framework import g_main_program
+from paddle.v2.fluid.framework import default_main_program
 import paddle.v2.fluid.core as core
 from paddle.v2.fluid.executor import Executor
 import paddle.v2.fluid.io as io
 from paddle.v2.fluid.initializer import ConstantInitializer
 import numpy as np
 
+main_program = default_main_program()
+
 
 class TestParameter(unittest.TestCase):
     def test_param(self):
         shape = [784, 100]
         val = 1.0625
-        b = g_main_program.global_block()
+        b = main_program.global_block()
         param = b.create_parameter(
             name='fc.w',
             shape=shape,
@@ -23,9 +25,9 @@ class TestParameter(unittest.TestCase):
         self.assertEqual(core.DataType.FP32, param.dtype)
         self.assertEqual(0, param.block.idx)
         exe = Executor(core.CPUPlace())
-        p = exe.run(g_main_program, fetch_list=[param])[0]
+        p = exe.run(main_program, fetch_list=[param])[0]
         self.assertTrue(np.allclose(p, np.ones(shape) * val))
-        p = io.get_parameter_value_by_name('fc.w', exe, g_main_program)
+        p = io.get_parameter_value_by_name('fc.w', exe, main_program)
         self.assertTrue(np.allclose(np.array(p), np.ones(shape) * val))
 
 

python/paddle/v2/fluid/tests/test_program.py

 from __future__ import print_function
 import unittest
 
-from paddle.v2.fluid.framework import Program
-from paddle.v2.fluid.framework import g_main_program
+from paddle.v2.fluid.framework import Program, default_main_program
 import paddle.v2.fluid.layers as layers
 
+main_program = default_main_program()
+
 
 class TestProgram(unittest.TestCase):
     def test_program(self):
-        b = g_main_program.current_block()
+        b = main_program.current_block()
         self.assertEqual(-1, b.parent_idx)
         self.assertEqual(0, b.idx)
 
-        b = g_main_program.create_block()
+        b = main_program.create_block()
         self.assertEqual(1, b.idx)
         self.assertEqual(0, b.parent_idx)
 
-        b = g_main_program.create_block()
+        b = main_program.create_block()
         self.assertEqual(2, b.idx)
         self.assertEqual(1, b.parent_idx)
 
-        g_main_program.rollback()
+        main_program.rollback()
 
-        b = g_main_program.current_block()
+        b = main_program.current_block()
         self.assertEqual(1, b.idx)
         self.assertEqual(0, b.parent_idx)
 
-        b = g_main_program.create_block()
+        b = main_program.create_block()
         self.assertEqual(3, b.idx)
         self.assertEqual(1, b.parent_idx)
 
-        g_main_program.rollback()
-        b = g_main_program.current_block()
+        main_program.rollback()
+        b = main_program.current_block()
         self.assertEqual(1, b.idx)
         self.assertEqual(0, b.parent_idx)
 

python/paddle/v2/fluid/tests/test_shrink_rnn_memory.py

@@ -3,9 +3,11 @@ import paddle.v2.fluid.core as core
 from paddle.v2.fluid.executor import Executor
 import paddle.v2.fluid.layers as layers
 from paddle.v2.fluid.backward import append_backward_ops
-from paddle.v2.fluid.framework import g_main_program
+from paddle.v2.fluid.framework import default_main_program
 import numpy
 
+main_program = default_main_program()
+
 
 class TestShrinkRNNMemory(unittest.TestCase):
     def test_shrink_rnn_memory(self):
@@ -36,7 +38,7 @@ class TestShrinkRNNMemory(unittest.TestCase):
         append_backward_ops(loss=mem3_mean)
         x_grad = exe.run(
             feed={'x': tensor},
-            fetch_list=[g_main_program.global_block().var('x@GRAD')])[0]
+            fetch_list=[main_program.global_block().var('x@GRAD')])[0]
         self.assertAlmostEqual(1.0, x_grad.sum(), delta=0.1)
 
 

python/paddle/v2/fluid/tests/test_variable.py

 import unittest
-from paddle.v2.fluid.framework import g_main_program, Program, convert_np_dtype_to_dtype_
+from paddle.v2.fluid.framework import default_main_program, Program, convert_np_dtype_to_dtype_
 import paddle.v2.fluid.core as core
 import numpy as np
 
@@ -18,7 +18,7 @@ class TestVariable(unittest.TestCase):
         self.assertRaises(ValueError, lambda: convert("int8"))
 
     def test_var(self):
-        b = g_main_program.current_block()
+        b = default_main_program().current_block()
         w = b.create_var(
             dtype="float64", shape=[784, 100], lod_level=0, name="fc.w")
         self.assertNotEqual(str(w), "")