提交 3e7819c2 编写于 作者: W wanghaoshuang

1. Reading image shape from input data instead of image_config

2. Add crop layer unitest
3. Fix bugs
上级 de5ded6b
......@@ -13,7 +13,7 @@
# limitations under the License
cmake_minimum_required(VERSION 3.0)
SET(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -ldl -lpthread")
set(CMAKE_MODULE_PATH ${CMAKE_MODULE_PATH} "${CMAKE_CURRENT_SOURCE_DIR}/cmake")
set(PROJ_ROOT ${CMAKE_CURRENT_SOURCE_DIR})
set(PROJ_BINARY_ROOT ${CMAKE_CURRENT_BINARY_DIR})
......
......@@ -22,11 +22,10 @@ template <>
void Crop<DEVICE_TYPE_CPU>(real* outputs,
const real* inputs,
const TensorShape inShape,
const TensorShape outShape,
const FuncConfig& conf) {
std::vector<uint32_t> crop_corner =
conf.get<std::vector<uint32_t>>("crop_corner");
std::vector<uint32_t> crop_shape =
conf.get<std::vector<uint32_t>>("crop_shape");
int cCrop = crop_corner[1];
int hCrop = crop_corner[2];
int wCrop = crop_corner[3];
......@@ -36,9 +35,9 @@ void Crop<DEVICE_TYPE_CPU>(real* outputs,
int inH = inShape[2];
int inW = inShape[3];
int outC = crop_shape[1];
int outH = crop_shape[2];
int outW = crop_shape[3];
int outC = outShape[1];
int outH = outShape[2];
int outW = outShape[3];
for (int n = 0; n < num; n++) {
for (int c = 0; c < outC; c++) {
......@@ -54,12 +53,11 @@ void Crop<DEVICE_TYPE_CPU>(real* outputs,
template <>
void CropGrad<DEVICE_TYPE_CPU>(const real* inGrad,
real* outGrad,
const TensorShape inShape,
const TensorShape outShape,
const FuncConfig& conf) {
std::vector<uint32_t> crop_corner =
conf.get<std::vector<uint32_t>>("crop_corner");
std::vector<uint32_t> crop_shape =
conf.get<std::vector<uint32_t>>("crop_shape");
int cCrop = crop_corner[1];
int hCrop = crop_corner[2];
int wCrop = crop_corner[3];
......@@ -69,9 +67,9 @@ void CropGrad<DEVICE_TYPE_CPU>(const real* inGrad,
int outH = outShape[2];
int outW = outShape[3];
int inC = crop_shape[1];
int inH = crop_shape[2];
int inW = crop_shape[3];
int inC = inShape[1];
int inH = inShape[2];
int inW = inShape[3];
for (int n = 0; n < num; n++) {
for (int c = 0; c < inC; c++) {
......@@ -123,9 +121,13 @@ public:
CHECK_EQ(outputs[0].getArgType(), ASSIGN_TO);
TensorShape inShape = inputs[0].shape();
TensorShape outShape = outputs[0].shape();
Crop<Device>(
outputs[0].data<real>(), inputs[0].data<real>(), inShape, conf_);
Crop<Device>(outputs[0].data<real>(),
inputs[0].data<real>(),
inShape,
outShape,
conf_);
}
private:
......@@ -152,9 +154,13 @@ public:
CHECK_EQ(outputs[0].getArgType(), ADD_TO);
TensorShape outShape = outputs[0].shape();
TensorShape inShape = inputs[0].shape();
CropGrad<Device>(
inputs[0].data<real>(), outputs[0].data<real>(), outShape, conf_);
CropGrad<Device>(inputs[0].data<real>(),
outputs[0].data<real>(),
inShape,
outShape,
conf_);
}
private:
......
......@@ -31,6 +31,7 @@ template <DeviceType Device>
void Crop(real* outputs,
const real* inputs,
const TensorShape inShape,
const TensorShape outShape,
const FuncConfig& conf);
/**
......@@ -45,5 +46,6 @@ template <DeviceType Device>
void CropGrad(const real* inGrad,
real* outGrad,
const TensorShape inShape,
const TensorShape outShape,
const FuncConfig& conf);
} // namespace paddle
......@@ -37,9 +37,9 @@ template <>
void Crop<DEVICE_TYPE_GPU>(real* outputs,
const real* inputs,
const TensorShape inShape,
const TensorShape outShape,
const FuncConfig& conf) {
std::vector<uint32_t> crop_corner = conf.get<std::vector<uint32_t>>("crop_corner");
std::vector<uint32_t> crop_shape = conf.get<std::vector<uint32_t>>("crop_shape");
int cropC = crop_corner[1];
int cropH = crop_corner[2];
int cropW = crop_corner[3];
......@@ -49,9 +49,9 @@ void Crop<DEVICE_TYPE_GPU>(real* outputs,
int inH = inShape[2];
int inW = inShape[3];
int outC = crop_shape[1];
int outH = crop_shape[2];
int outW = crop_shape[3];
int outC = outShape[1];
int outH = outShape[2];
int outW = outShape[3];
size_t nth = num * outC * outH * outW;
int blockSize = 1024;
......@@ -83,10 +83,10 @@ __global__ void KeCropDiff(const real* inGrad, real* outGrad,
template <>
void CropGrad<DEVICE_TYPE_GPU>(const real* inGrad,
real* outGrad,
const TensorShape inShape,
const TensorShape outShape,
const FuncConfig& conf) {
std::vector<uint32_t> crop_corner = conf.get<std::vector<uint32_t>>("crop_corner");
std::vector<uint32_t> crop_shape = conf.get<std::vector<uint32_t>>("crop_shape");
int cropC = crop_corner[1];
int cropH = crop_corner[2];
int cropW = crop_corner[3];
......@@ -96,9 +96,9 @@ void CropGrad<DEVICE_TYPE_GPU>(const real* inGrad,
int outH = outShape[2];
int outW = outShape[3];
int inC = crop_shape[1];
int inH = crop_shape[2];
int inW = crop_shape[3];
int inC = inShape[1];
int inH = inShape[2];
int inW = inShape[3];
size_t nth = num * inC * inH * inW;
int blockSize = 1024;
......
......@@ -22,7 +22,8 @@ bool CropLayer::init(const LayerMap& layerMap,
const ParameterMap& parameterMap) {
/* Initialize the basic parent class */
Layer::init(layerMap, parameterMap);
CHECK_LE(static_cast<int>(inputLayers_.size()), 2);
CHECK_GE(static_cast<int>(inputLayers_.size()), 1);
crop_axis_ = config_.axis();
for (int i = 0; i < config_.offset_size(); i++) {
crop_offsets_.push_back(config_.offset(i));
......@@ -36,8 +37,14 @@ bool CropLayer::init(const LayerMap& layerMap,
? input0_img_conf.img_size_y()
: input0_img_conf.img_size(),
input0_img_conf.img_size()});
// 2. get output shape from input_1 or crop shap conf
if (config_.inputs_size() == 2) {
// 2. get target dims from config
if (config_.inputs_size() == 1) {
targetDims_ = TensorShape({config_.shape(0),
config_.shape(1),
config_.shape(2),
config_.shape(3)});
} else {
// 2. get input_1 shape
auto& input1_img_conf = config_.inputs(1).image_conf();
targetDims_ = TensorShape({0,
input1_img_conf.channels(),
......@@ -45,24 +52,10 @@ bool CropLayer::init(const LayerMap& layerMap,
? input1_img_conf.img_size_y()
: input1_img_conf.img_size(),
input1_img_conf.img_size()});
} else {
targetDims_ = TensorShape({config_.shape(0),
config_.shape(1),
config_.shape(2),
config_.shape(3)});
}
// 3. get final crop shape
// 3. get final crop corner
int dimSize = 4;
for (int i = 0; i < dimSize; i++) {
if (i >= crop_axis_) {
crop_shape_.push_back(targetDims_[i]);
} else {
crop_shape_.push_back(inDims_[i]);
}
}
// 4. get final crop corner
crop_corner_ = {0, 0, 0, 0};
for (int i = 0; i < dimSize; i++) {
if (i >= crop_axis_) {
......@@ -75,43 +68,61 @@ bool CropLayer::init(const LayerMap& layerMap,
}
outDims_ = TensorShape(4);
setOutDims(0);
createFunction(forward_,
"Crop",
FuncConfig()
.set("crop_corner", crop_corner_)
.set("crop_shape", crop_shape_));
createFunction(backward_,
"CropGrad",
FuncConfig()
.set("crop_corner", crop_corner_)
.set("crop_shape", crop_shape_));
createFunction(
forward_, "Crop", FuncConfig().set("crop_corner", crop_corner_));
createFunction(
backward_, "CropGrad", FuncConfig().set("crop_corner", crop_corner_));
return true;
}
void CropLayer::setOutDims(const size_t batchSize) {
outDims_.reshape({batchSize, crop_shape_[1], crop_shape_[2], crop_shape_[3]});
void CropLayer::setOutDims() {
MatrixPtr input = inputLayers_[1]->getOutputValue();
size_t batchSize = input->getHeight();
// get target dims from input_1
if (config_.inputs_size() == 2) {
targetDims_.setDim(0, batchSize);
int ch = config_.inputs(0).image_conf().channels();
if (ch != 0) targetDims_.setDim(1, ch);
int h = inputLayers_[1]->getOutput().getFrameHeight();
if (h != 0) targetDims_.setDim(2, h);
int w = inputLayers_[1]->getOutput().getFrameWidth();
if (w != 0) targetDims_.setDim(3, w);
}
// get final crop shape from target dims and crop axis
std::vector<uint32_t> crop_shape;
int dimSize = 4;
for (int i = 0; i < dimSize; i++) {
if (i >= crop_axis_) {
crop_shape.push_back(targetDims_[i]);
} else {
crop_shape.push_back(inDims_[i]);
}
}
outDims_.reshape(
{crop_shape[0], crop_shape[1], crop_shape[2], crop_shape[3]});
output_.setFrameHeight(crop_shape[2]);
output_.setFrameWidth(crop_shape[3]);
}
void CropLayer::setTensorDim(const size_t batchSize) {
CHECK_EQ(static_cast<int>(inputLayers_.size()), 2);
void CropLayer::setInDims() {
MatrixPtr input = inputLayers_[0]->getOutputValue();
size_t batchSize = input->getHeight();
inDims_.setDim(0, batchSize);
int h = inputLayers_[0]->getOutput().getFrameHeight();
if (h != 0) inDims_.setDim(2, h);
int w = inputLayers_[0]->getOutput().getFrameWidth();
if (w != 0) inDims_.setDim(3, w);
setOutDims(batchSize);
}
void CropLayer::forward(PassType passType) {
Layer::forward(passType);
MatrixPtr input = inputLayers_[0]->getOutputValue();
size_t batchSize = input->getHeight();
setTensorDim(batchSize);
setInDims();
setOutDims();
int size = outDims_[1] * outDims_[2] * outDims_[3];
resetOutput(batchSize, size);
resetOutput(outDims_[0], size);
MatrixPtr outV = getOutputValue();
REGISTER_TIMER_INFO("CropForward", getName().c_str());
......
......@@ -39,13 +39,12 @@ public:
void backward(const UpdateCallback& callback = nullptr) override;
protected:
void setOutDims(const size_t batchSize);
void setTensorDim(const size_t batchSize);
void setOutDims();
void setInDims();
int32_t crop_axis_;
std::vector<uint32_t> crop_offsets_;
std::vector<uint32_t> crop_corner_;
std::vector<uint32_t> crop_shape_;
TensorShape inDims_;
TensorShape targetDims_;
TensorShape outDims_;
......
......@@ -2005,29 +2005,6 @@ class CropLayer(LayerBase):
image_conf.img_size_y = input_layer.height
image_conf.channels = input_layer.size / (input_layer.width *
input_layer.height)
out_ch = image_conf.channels
out_h = image_conf.img_size
out_w = image_conf.img_size_y
if len(self.inputs) == 2:
# get channels, width and height from input_1 layer
input_layer = self.get_input_layer(1)
image_conf = self.config.inputs[1].image_conf
image_conf.img_size = input_layer.width
image_conf.img_size_y = input_layer.height
image_conf.channels = input_layer.size / (input_layer.width *
input_layer.height)
out_ch = image_conf.channels
out_h = image_conf.img_size_y
out_w = image_conf.img_size
else:
# set channels, width and heigth of current layer
if len(shape) > 2:
out_ch = shape[-3]
if len(shape) > 1:
out_h = shape[-2]
if len(shape) > 0:
out_w = shape[-1]
self.set_cnn_layer(name, out_h, out_w, out_ch)
@config_layer('batch_norm')
......
......@@ -5881,9 +5881,9 @@ def prelu_layer(input,
@wrap_name_default()
@layer_support()
def crop_layer(input, axis, offset, shape=None, name=None, layer_attr=None):
def crop_layer(input, offset, axis=2, shape=None, name=None, layer_attr=None):
"""
The crop layer crop images by offset and shape. User can set crop shape by
The crop layer crops images by offset and shape. User can set crop shape by
args 'shape' explicitly or by reference input layer.
......@@ -5896,16 +5896,16 @@ def crop_layer(input, axis, offset, shape=None, name=None, layer_attr=None):
:param input: The input layer.If two inputs were setted,
the second input will be regarded as reference input
:type input: LayerOutput or Sequence
:param offset: The crop offset
:type offset: Sequence
:param axis: start axis to be cropped. To image input layer:
- 0: batch size
- 1: channels
- 2: height
- 3: width
:type partial_sum: int
:param offset: The crop offset
:type offset: Sequence
:param shape: The shape to be cropped. Default is None.
:type shape: Sqquence | None
:type shape: Sequence | None
:param name: Name of this layer.
:type name: basestring
:return: LayerOutput object.
......@@ -5913,8 +5913,6 @@ def crop_layer(input, axis, offset, shape=None, name=None, layer_attr=None):
"""
if isinstance(input, LayerOutput):
input = [input]
elif isinstance(input, Projection):
input = [input]
else:
assert isinstance(input, collections.Sequence)
l = Layer(
......
from paddle.trainer_config_helpers import *
settings(batch_size=1000, learning_rate=1e-5)
data = data_layer(name='data', size=2016, height=48, width=42)
refernce_data = data_layer(name='data', size=768, height=16, width=16)
conv = img_conv_layer(
input=data,
filter_size=3,
num_channels=1,
num_filters=16,
padding=1,
act=LinearActivation(),
bias_attr=True)
pool = img_pool_layer(input=conv, pool_size=2, stride=2, pool_type=MaxPooling())
crop = crop_layer(input=[pool, refernce_data], axis=2)
outputs(pad)
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