提交 0be34949 编写于 作者: C chengduo 提交者: GitHub

Merge pull request #3594 from chengduoZH/Adapting_to_the_BatchNorm_structure_to_support_3D_data

Adapting to the BatchNorm structure to support 3D data
......@@ -62,14 +62,18 @@ void BatchNormBaseLayer::calFeatureMapSize() {
const ImageConfig& conf = config_.inputs(0).image_conf();
imageH_ = inputLayers_[0]->getOutput().getFrameHeight();
imageW_ = inputLayers_[0]->getOutput().getFrameWidth();
imageD_ = inputLayers_[0]->getOutput().getFrameDepth();
if (0 == imageD_) imageD_ = conf.img_size_z();
if (imageH_ == 0 && imageW_ == 0) {
imageH_ = conf.has_img_size_y() ? conf.img_size_y() : conf.img_size();
imageW_ = conf.img_size();
} else {
getOutput().setFrameHeight(imageH_);
getOutput().setFrameWidth(imageW_);
getOutput().setFrameDepth(imageD_);
}
imgPixels_ = imageH_ * imageW_;
imgPixels_ = imageH_ * imageW_ * imageD_;
}
} // namespace paddle
......@@ -80,6 +80,7 @@ protected:
/// Height or width of input image feature.
/// Both of them are 1 if the input is fully-connected layer.
int imageD_;
int imageH_;
int imageW_;
/// Height * Width.
......
......@@ -37,7 +37,7 @@ bool CudnnBatchNormLayer::init(const LayerMap& layerMap,
}
void CudnnBatchNormLayer::reshape(int batchSize) {
hl_tensor_reshape(ioDesc_, batchSize, channels_, imageH_, imageW_);
hl_tensor_reshape(ioDesc_, batchSize, channels_, imageH_ * imageD_, imageW_);
}
void CudnnBatchNormLayer::forward(PassType passType) {
......@@ -104,7 +104,7 @@ void CudnnBatchNormLayer::forward(PassType passType) {
EPS,
batchSize,
channels_,
imageH_,
imageH_ * imageD_,
imageW_);
}
}
......
......@@ -1703,6 +1703,55 @@ TEST(Layer, BatchNormalizationLayer) {
#endif
}
void testBatchNorm3DLayer(const string& type, bool trans, bool useGpu) {
TestConfig config;
const int CHANNELS = 10;
const int IMG_SIZE = 16;
const int IMG_SIZE_Y = 8;
const int IMG_SIZE_Z = 8;
size_t size = CHANNELS * IMG_SIZE * IMG_SIZE_Y * IMG_SIZE_Z;
config.layerConfig.set_type(type);
config.layerConfig.set_size(size);
config.layerConfig.set_active_type("sigmoid");
config.biasSize = CHANNELS;
config.inputDefs.push_back({INPUT_DATA,
"layer_0",
/* dim= */ size,
/* paraSize= */ CHANNELS});
config.inputDefs.push_back({INPUT_DATA, "layer_1_running_mean", 1, CHANNELS});
config.inputDefs.back().isStatic = true;
config.inputDefs.push_back({INPUT_DATA, "layer_2_running_var", 1, CHANNELS});
config.inputDefs.back().isStatic = true;
LayerInputConfig* input = config.layerConfig.add_inputs();
config.layerConfig.add_inputs();
config.layerConfig.add_inputs();
ImageConfig* img_conf = input->mutable_image_conf();
img_conf->set_channels(CHANNELS);
img_conf->set_img_size(IMG_SIZE);
img_conf->set_img_size_y(IMG_SIZE_Y);
img_conf->set_img_size_z(IMG_SIZE_Z);
testLayerGrad(config,
"batch_norm",
64,
/* trans= */ trans,
useGpu,
/* useWeight */ true);
}
TEST(Layer, testBatchNorm3DLayer) {
testBatchNorm3DLayer("batch_norm", false, false);
#ifndef PADDLE_ONLY_CPU
testBatchNorm3DLayer("batch_norm", false, true);
if (hl_get_cudnn_lib_version() >= int(4000)) {
testBatchNorm3DLayer("cudnn_batch_norm", false, true);
}
#endif
}
void testConvOperator(bool isDeconv) {
TestConfig config;
const int NUM_FILTERS = 16;
......
......@@ -520,6 +520,7 @@ message LayerConfig {
// for HuberRegressionLoss
optional double delta = 57 [ default = 1.0 ];
// for 3D data
optional uint64 depth = 58 [ default = 1 ];
// for switch order layer
......
......@@ -1332,6 +1332,12 @@ def parse_image(image, input_layer_name, image_conf):
get_img_size(input_layer_name, image_conf.channels)
def parse_image3d(image, input_layer_name, image_conf):
image_conf.channels = image.channels
image_conf.img_size, image_conf.img_size_y, image_conf.img_size_z = \
get_img3d_size(input_layer_name, image_conf.channels)
def parse_norm(norm, input_layer_name, norm_conf):
norm_conf.norm_type = norm.norm_type
config_assert(
......@@ -2365,6 +2371,7 @@ class BatchNormLayer(LayerBase):
name,
inputs,
bias=True,
img3D=False,
use_global_stats=True,
moving_average_fraction=0.9,
batch_norm_type=None,
......@@ -2410,13 +2417,31 @@ class BatchNormLayer(LayerBase):
input_layer = self.get_input_layer(0)
image_conf = self.config.inputs[0].image_conf
if img3D:
parse_image3d(self.inputs[0].image, input_layer.name, image_conf)
# Only pass the width and height of input to batch_norm layer
# when either of it is non-zero.
if input_layer.width != 0 or input_layer.height != 0:
self.set_cnn_layer(
input_layer_name=name,
depth=image_conf.img_size_z,
height=image_conf.img_size_y,
width=image_conf.img_size,
channels=image_conf.channels,
is_print=True)
else:
self.set_layer_size(input_layer.size)
else:
parse_image(self.inputs[0].image, input_layer.name, image_conf)
# Only pass the width and height of input to batch_norm layer
# when either of it is non-zero.
if input_layer.width != 0 or input_layer.height != 0:
self.set_cnn_layer(name, image_conf.img_size_y, image_conf.img_size,
image_conf.channels, False)
self.set_cnn_layer(
input_layer_name=name,
height=image_conf.img_size_y,
width=image_conf.img_size,
channels=image_conf.channels,
is_print=True)
else:
self.set_layer_size(input_layer.size)
......@@ -2433,6 +2458,28 @@ class BatchNormLayer(LayerBase):
self.create_bias_parameter(bias, psize)
def set_cnn_layer(self,
input_layer_name,
depth=None,
height=None,
width=None,
channels=None,
is_print=True):
depthIsNone = False
if depth is None:
depth = 1
depthIsNone = True
size = depth * height * width * channels
self.set_layer_size(size)
self.set_layer_height_width(height, width)
self.set_layer_depth(depth)
if is_print and depthIsNone:
print("output for %s: c = %d, h = %d, w = %d, size = %d" %
(input_layer_name, channels, height, width, size))
elif is_print:
print("output for %s: c = %d, d = %d, h = %d, w = %d, size = %d" %
(input_layer_name, channels, depth, height, width, size))
def calc_parameter_size(self, image_conf):
return image_conf.channels
......@@ -2694,9 +2741,20 @@ class AddToLayer(LayerBase):
super(AddToLayer, self).__init__(
name, 'addto', 0, inputs=inputs, **xargs)
config_assert(len(inputs) > 0, 'inputs cannot be empty for AddToLayer')
if len(self.inputs) > 1:
for input_index in xrange(len(self.inputs)):
input_layer = self.get_input_layer(input_index)
self.set_layer_size(input_layer.size)
assert self.get_input_layer(0).height == self.get_input_layer(
input_index).height
assert self.get_input_layer(0).width == self.get_input_layer(
input_index).width
assert self.get_input_layer(0).depth == self.get_input_layer(
input_index).depth
self.set_layer_size(self.get_input_layer(0).size)
self.set_layer_height_width(self.get_input_layer(0).height, \
self.get_input_layer(0).width)
self.set_layer_depth(self.get_input_layer(0).depth)
self.create_bias_parameter(bias, self.config.size)
......@@ -3376,11 +3434,20 @@ class ConcatenateLayer(LayerBase):
name, 'concat', 0, inputs=inputs, **xargs)
size = 0
for input_index in xrange(len(self.inputs)):
assert self.get_input_layer(0).height == self.get_input_layer(
input_index).height
assert self.get_input_layer(0).width == self.get_input_layer(
input_index).width
assert self.get_input_layer(0).depth == self.get_input_layer(
input_index).depth
input_layer = self.get_input_layer(input_index)
input = self.inputs[input_index]
if self.config.size == 0:
size += input_layer.size
self.set_layer_height_width(self.get_input_layer(0).height, \
self.get_input_layer(0).width)
self.set_layer_depth(self.get_input_layer(0).depth)
self.set_layer_size(size)
......
......@@ -354,6 +354,10 @@ class LayerOutput(object):
def height(self):
return cp.g_layer_map[self.full_name].height
@property
def depth(self):
return cp.g_layer_map[self.full_name].depth
def set_input(self, input):
"""
Set the input for a memory layer. Can only be used for memory layer
......@@ -2953,6 +2957,7 @@ def img_cmrnorm_layer(input,
def batch_norm_layer(input,
act=None,
name=None,
img3D=False,
num_channels=None,
bias_attr=None,
param_attr=None,
......@@ -3042,6 +3047,7 @@ def batch_norm_layer(input,
(batch_norm_type == "cudnn_batch_norm")
l = Layer(
name=name,
img3D=img3D,
inputs=Input(
input.name, image=Image(channels=num_channels), **param_attr.attr),
active_type=act.name,
......
......@@ -10,6 +10,6 @@ test_prelu_layer test_row_conv test_detection_output_layer test_multibox_loss_la
test_recursive_topology test_gated_unit_layer test_clip_layer test_row_l2_norm_layer
test_kmax_seq_socre_layer test_sub_nested_seq_select_layer test_scale_shift_layer
test_seq_slice_layer test_cross_entropy_over_beam test_pooling3D_layer
test_conv3d_layer test_deconv3d_layer)
test_conv3d_layer test_deconv3d_layer test_BatchNorm3D)
export whole_configs=(test_split_datasource)
......@@ -62,6 +62,7 @@ layers {
moving_average_fraction: 0.9
height: 227
width: 227
depth: 1
}
layers {
name: "__crmnorm_0__"
......
......@@ -62,6 +62,7 @@ layers {
moving_average_fraction: 0.9
height: 256
width: 256
depth: 1
}
layers {
name: "__crmnorm_0__"
......
type: "nn"
layers {
name: "data3D"
type: "data"
size: 360
active_type: ""
height: 6
width: 20
depth: 3
}
layers {
name: "__batch_norm_0__"
type: "batch_norm"
size: 360
active_type: "relu"
inputs {
input_layer_name: "data3D"
input_parameter_name: "___batch_norm_0__.w0"
image_conf {
channels: 1
img_size: 20
img_size_y: 6
img_size_z: 3
}
}
inputs {
input_layer_name: "data3D"
input_parameter_name: "___batch_norm_0__.w1"
}
inputs {
input_layer_name: "data3D"
input_parameter_name: "___batch_norm_0__.w2"
}
bias_parameter_name: "___batch_norm_0__.wbias"
moving_average_fraction: 0.9
height: 6
width: 20
depth: 3
}
parameters {
name: "___batch_norm_0__.w0"
size: 1
initial_mean: 1.0
initial_std: 0.0
initial_strategy: 0
initial_smart: false
}
parameters {
name: "___batch_norm_0__.w1"
size: 1
initial_mean: 0.0
initial_std: 0.0
dims: 1
dims: 1
initial_strategy: 0
initial_smart: false
is_static: true
is_shared: true
}
parameters {
name: "___batch_norm_0__.w2"
size: 1
initial_mean: 0.0
initial_std: 0.0
dims: 1
dims: 1
initial_strategy: 0
initial_smart: false
is_static: true
is_shared: true
}
parameters {
name: "___batch_norm_0__.wbias"
size: 1
initial_mean: 0.0
initial_std: 0.0
dims: 1
dims: 1
initial_strategy: 0
initial_smart: false
}
input_layer_names: "data3D"
output_layer_names: "__batch_norm_0__"
sub_models {
name: "root"
layer_names: "data3D"
layer_names: "__batch_norm_0__"
input_layer_names: "data3D"
output_layer_names: "__batch_norm_0__"
is_recurrent_layer_group: false
}
......@@ -74,6 +74,9 @@ layers {
inputs {
input_layer_name: "__bidirectional_gru_0___bw"
}
height: 0
width: 0
depth: 1
}
parameters {
name: "___bidirectional_gru_0___fw_transform.w0"
......
......@@ -16,6 +16,9 @@ layers {
inputs {
input_layer_name: "data"
}
height: 0
width: 0
depth: 1
}
layers {
name: "__addto_1__"
......@@ -28,6 +31,9 @@ layers {
inputs {
input_layer_name: "__addto_0__"
}
height: 0
width: 0
depth: 1
}
layers {
name: "__addto_2__"
......@@ -40,6 +46,9 @@ layers {
inputs {
input_layer_name: "__addto_1__"
}
height: 0
width: 0
depth: 1
}
layers {
name: "__addto_3__"
......@@ -52,6 +61,9 @@ layers {
inputs {
input_layer_name: "__addto_2__"
}
height: 0
width: 0
depth: 1
}
layers {
name: "__addto_4__"
......@@ -64,6 +76,9 @@ layers {
inputs {
input_layer_name: "__addto_3__"
}
height: 0
width: 0
depth: 1
}
layers {
name: "__addto_5__"
......@@ -76,6 +91,9 @@ layers {
inputs {
input_layer_name: "__addto_4__"
}
height: 0
width: 0
depth: 1
}
layers {
name: "__addto_6__"
......@@ -88,6 +106,9 @@ layers {
inputs {
input_layer_name: "__addto_5__"
}
height: 0
width: 0
depth: 1
}
layers {
name: "__addto_7__"
......@@ -100,6 +121,9 @@ layers {
inputs {
input_layer_name: "__addto_6__"
}
height: 0
width: 0
depth: 1
}
layers {
name: "__addto_8__"
......@@ -112,6 +136,9 @@ layers {
inputs {
input_layer_name: "__addto_7__"
}
height: 0
width: 0
depth: 1
}
layers {
name: "__addto_9__"
......@@ -124,6 +151,9 @@ layers {
inputs {
input_layer_name: "__addto_8__"
}
height: 0
width: 0
depth: 1
}
layers {
name: "__addto_10__"
......@@ -136,6 +166,9 @@ layers {
inputs {
input_layer_name: "__addto_9__"
}
height: 0
width: 0
depth: 1
}
layers {
name: "__addto_11__"
......@@ -148,6 +181,9 @@ layers {
inputs {
input_layer_name: "__addto_10__"
}
height: 0
width: 0
depth: 1
}
layers {
name: "__addto_12__"
......@@ -160,6 +196,9 @@ layers {
inputs {
input_layer_name: "__addto_11__"
}
height: 0
width: 0
depth: 1
}
layers {
name: "__addto_13__"
......@@ -172,6 +211,9 @@ layers {
inputs {
input_layer_name: "__addto_12__"
}
height: 0
width: 0
depth: 1
}
layers {
name: "__addto_14__"
......@@ -184,6 +226,9 @@ layers {
inputs {
input_layer_name: "__addto_13__"
}
height: 0
width: 0
depth: 1
}
layers {
name: "__addto_15__"
......@@ -196,6 +241,9 @@ layers {
inputs {
input_layer_name: "__addto_14__"
}
height: 0
width: 0
depth: 1
}
layers {
name: "__addto_16__"
......@@ -208,6 +256,9 @@ layers {
inputs {
input_layer_name: "__addto_15__"
}
height: 0
width: 0
depth: 1
}
layers {
name: "__addto_17__"
......@@ -220,6 +271,9 @@ layers {
inputs {
input_layer_name: "__addto_16__"
}
height: 0
width: 0
depth: 1
}
layers {
name: "__addto_18__"
......@@ -232,6 +286,9 @@ layers {
inputs {
input_layer_name: "__addto_17__"
}
height: 0
width: 0
depth: 1
}
layers {
name: "__addto_19__"
......@@ -244,6 +301,9 @@ layers {
inputs {
input_layer_name: "__addto_18__"
}
height: 0
width: 0
depth: 1
}
layers {
name: "__addto_20__"
......@@ -256,6 +316,9 @@ layers {
inputs {
input_layer_name: "__addto_19__"
}
height: 0
width: 0
depth: 1
}
layers {
name: "__addto_21__"
......@@ -268,6 +331,9 @@ layers {
inputs {
input_layer_name: "__addto_20__"
}
height: 0
width: 0
depth: 1
}
layers {
name: "__addto_22__"
......@@ -280,6 +346,9 @@ layers {
inputs {
input_layer_name: "__addto_21__"
}
height: 0
width: 0
depth: 1
}
layers {
name: "__addto_23__"
......@@ -292,6 +361,9 @@ layers {
inputs {
input_layer_name: "__addto_22__"
}
height: 0
width: 0
depth: 1
}
layers {
name: "__addto_24__"
......@@ -304,6 +376,9 @@ layers {
inputs {
input_layer_name: "__addto_23__"
}
height: 0
width: 0
depth: 1
}
layers {
name: "__addto_25__"
......@@ -316,6 +391,9 @@ layers {
inputs {
input_layer_name: "__addto_24__"
}
height: 0
width: 0
depth: 1
}
layers {
name: "__addto_26__"
......@@ -328,6 +406,9 @@ layers {
inputs {
input_layer_name: "__addto_25__"
}
height: 0
width: 0
depth: 1
}
layers {
name: "__addto_27__"
......@@ -340,6 +421,9 @@ layers {
inputs {
input_layer_name: "__addto_26__"
}
height: 0
width: 0
depth: 1
}
layers {
name: "__addto_28__"
......@@ -352,6 +436,9 @@ layers {
inputs {
input_layer_name: "__addto_27__"
}
height: 0
width: 0
depth: 1
}
layers {
name: "__addto_29__"
......@@ -364,6 +451,9 @@ layers {
inputs {
input_layer_name: "__addto_28__"
}
height: 0
width: 0
depth: 1
}
layers {
name: "__addto_30__"
......@@ -376,6 +466,9 @@ layers {
inputs {
input_layer_name: "__addto_29__"
}
height: 0
width: 0
depth: 1
}
layers {
name: "__addto_31__"
......@@ -388,6 +481,9 @@ layers {
inputs {
input_layer_name: "__addto_30__"
}
height: 0
width: 0
depth: 1
}
layers {
name: "__fc_layer_0__"
......
......@@ -22,6 +22,9 @@ layers {
inputs {
input_layer_name: "b"
}
height: 0
width: 0
depth: 1
}
layers {
name: "__concat_0__"
......@@ -34,6 +37,9 @@ layers {
inputs {
input_layer_name: "b"
}
height: 0
width: 0
depth: 1
}
layers {
name: "__concat_1__"
......
from paddle.trainer_config_helpers import *
settings(batch_size=1000, learning_rate=1e-4)
#data = data_layer(name='data', size=180, width=30, height=6)
#batchNorm = batch_norm_layer(data, num_channels=1)
#outputs(batchNorm)
data3D = data_layer(name='data3D', size=120 * 3, width=20, height=6, depth=3)
batchNorm3D = batch_norm_layer(data3D, num_channels=1, img3D=True)
outputs(batchNorm3D)
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册