[caffe笔记007]：在新版caffe中实现Holistically-Nested Edge Detection
写在最前面：“Holistically-Nested Edge Detection ”(HED)是Zhuowen Tu老师组的博士生Saining Xie发表在ICCV15年的做边缘检测的文章，获得了ICCV马尔奖提名。
Paper: http://arxiv.org/abs/1504.06375
Github: https://github.com/s9xie/hed
补充：HED在新版caffe中的实现可以直接使用https://github.com/yun-liu/rcf 提供的版本。
写在前面：HED的作者Saining Xie提供的caffe版本比较老，源代码和最新版的caffe有很大的不同。在使用新版caffe训练HED的时候，需要添加HED使用的层，分别是：
1. 在caffe.prototxt添加相关层信息和参数
2. base_data_layer中添加LabelmapBatch类和BasePrefetchingLabelmapDataLayer类。
3. 修改blocking_queue.cpp以支持LabelmapBatch。
4. 添加新层image_labelmap_data_layer，该层由BasePrefetchingLabelmapDataLayer派生。
5. 添加HED使用loss层sigmoid_cross_entropy_loss_hed_layer。因为HED中重新实现了加权cross_entropy_loss
6. 添加HED使用crop层crop_hed_layer。因为HED中的crop是以中心点为参考进行crop，和caffe中不一样
BSDS500性能测试：在BSDS500边缘检测数据集上达到了F-measure=0.776（Saining Xie提供的HED版本为0.780）
1. caffe.prototxt
message LayerParameter不用做修改。因为image_labelmap_data_layer和image_data_layer使用共同的参数结构；sigmoid_cross_entropy_loss_hed_layer和sigmoid_layer使用共同的参数结构;crop_hed_layer没有参数。
message V1LayerParameter的LayerType中添加这两层的层名(编号不重复就行)：
IMAGE_LABELMAP_DATA = 43;
SIGMOID_CROSS_ENTROPY_LOSS_HED = 44;
CROP_HED = 45;2. base_data_layer
头文件base_data_layer.hpp:
在caffe命名空间中添加LabelmapBatch和BasePrefetchingLabelmapDataLayer类。
template <typename Dtype>
class LabelmapBatch {
public:
Blob data_, labelmap_;
};
template <typename Dtype>
class BasePrefetchingLabelmapDataLayer :
public BaseDataLayer, public InternalThread {
public:
explicit BasePrefetchingLabelmapDataLayer(const LayerParameter& param);
// LayerSetUp: implements common data layer setup functionality, and calls
// DataLayerSetUp to do special data layer setup for individual layer types.
// This method may not be overridden.
void LayerSetUp(const vector* labelmapbatch) = 0;
LabelmapBatch prefetch_[PREFETCH_COUNT];
BlockingQueue*> prefetch_free_;
BlockingQueue*> prefetch_full_;
Blob transformed_data_;
Blob transformed_labelmap_;
}; cpp源文件base_data_layer.cpp:
头文件中成员函数的实现：
template <typename Dtype>
BasePrefetchingLabelmapDataLayer::BasePrefetchingLabelmapDataLayer(
const LayerParameter& param)
: BaseDataLayer(param),
prefetch_free_(), prefetch_full_() {
for (int i = 0; i < PREFETCH_COUNT; ++i) {
prefetch_free_.push(&prefetch_[i]);
}
}
template <typename Dtype>
void BasePrefetchingLabelmapDataLayer::LayerSetUp(
const vector::LayerSetUp(bottom, top);
// Before starting the prefetch thread, we make cpu_data and gpu_data
// calls so that the prefetch thread does not accidentally make simultaneous
// cudaMalloc calls when the main thread is running. In some GPUs this
// seems to cause failures if we do not so.
for (int i = 0; i < PREFETCH_COUNT; ++i) {
prefetch_[i].data_.mutable_cpu_data();
prefetch_[i].labelmap_.mutable_cpu_data();
}
#ifndef CPU_ONLY
if (Caffe::mode() == Caffe::GPU) {
for (int i = 0; i < PREFETCH_COUNT; ++i) {
prefetch_[i].data_.mutable_gpu_data();
prefetch_[i].labelmap_.mutable_gpu_data();
}
}
#endif
DLOG(INFO) << "Initializing prefetch";
this->data_transformer_->InitRand();
StartInternalThread();
DLOG(INFO) << "Prefetch initialized.";
}
template <typename Dtype>
void BasePrefetchingLabelmapDataLayer::InternalThreadEntry() {
#ifndef CPU_ONLY
cudaStream_t stream;
if (Caffe::mode() == Caffe::GPU) {
CUDA_CHECK(cudaStreamCreateWithFlags(&stream, cudaStreamNonBlocking));
}
#endif
try {
while (!must_stop()) {
LabelmapBatch* batch = prefetch_free_.pop();
load_batch(batch);
#ifndef CPU_ONLY
if (Caffe::mode() == Caffe::GPU) {
batch->data_.data().get()->async_gpu_push(stream);
CUDA_CHECK(cudaStreamSynchronize(stream));
}
#endif
prefetch_full_.push(batch);
}
} catch (boost::thread_interrupted&) {
// Interrupted exception is expected on shutdown
}
#ifndef CPU_ONLY
if (Caffe::mode() == Caffe::GPU) {
CUDA_CHECK(cudaStreamDestroy(stream));
}
#endif
}
template <typename Dtype>
void BasePrefetchingLabelmapDataLayer::Forward_cpu(
const vector* batch = prefetch_full_.pop("Data layer prefetch queue empty");
// Reshape to loaded data.
top[0]->ReshapeLike(batch->data_);
// Copy the data
caffe_copy(batch->data_.count(), batch->data_.cpu_data(),
top[0]->mutable_cpu_data());
DLOG(INFO) << "Prefetch copied";
// Reshape to loaded labels.
top[1]->ReshapeLike(batch->labelmap_);
// Copy the labels.
caffe_copy(batch->labelmap_.count(), batch->labelmap_.cpu_data(),
top[1]->mutable_cpu_data());
prefetch_free_.push(batch);
} #ifdef CPU_ONLY
STUB_GPU_FORWARD(BasePrefetchingLabelmapDataLayer, Forward);
#endif
INSTANTIATE_CLASS(BasePrefetchingLabelmapDataLayer);cu源文件base_data_layer.cu:
template <typename Dtype>
void BasePrefetchingLabelmapDataLayer::Forward_gpu(
const vector* batch = prefetch_full_.pop("Data layer prefetch queue empty");
// Reshape to loaded data.
top[0]->ReshapeLike(batch->data_);
// Copy the data
caffe_copy(batch->data_.count(), batch->data_.gpu_data(),
top[0]->mutable_gpu_data());
top[1]->ReshapeLike(batch->labelmap_);
// Copy the labels.
caffe_copy(batch->labelmap_.count(), batch->labelmap_.gpu_data(),
top[1]->mutable_gpu_data());
// Ensure the copy is synchronous wrt the host, so that the next batch isn't
// copied in meanwhile.
CUDA_CHECK(cudaStreamSynchronize(cudaStreamDefault));
prefetch_free_.push(batch);
} INSTANTIATE_LAYER_GPU_FORWARD(BasePrefetchingLabelmapDataLayer);3. blocking_queue.cpp
改文件位于$CAFFE_ROOT/src/caffe/util/中。
template class BlockingQueue<LabelmapBatch<float>*>;
template class BlockingQueue<LabelmapBatch<double>*>;4. image_labelmap_data_layer
拷贝代码
直接将HED中的该层的头文件和源文件拷贝到相应的位置。
修改代码
可参考image_data_layer.hpp和image_data_layer.cpp中包含的头文件。
5. sigmoid_cross_entropy_loss_hed_layer
拷贝代码
将HED中的sigmoid_cross_entropy_loss层的头文件和源文件重命名后，拷贝到相应的位置。
修改代码
- 修改包含的头文件
- 修改类名称
6. crop_hed_layer
拷贝代码
将caffe中的crop_layer.cpp,crop_layer.cu和crop_layer.hpp重新复制一份并命名为crop_hed_layer
修改代码
- 修改包含的头文件
- 修改类名称
- 修改
crop_hed_layer.cpp中的LayerSetUp和Reshape函数。
template <typename Dtype>
void CropHedLayer::LayerSetUp(const vector::Reshape(const vector