void DataLayer<Dtype>::InternalThreadEntry() { Datum datum; CHECK(this->prefetch_data_.count()); Dtype* top_data = this->prefetch_data_.mutable_cpu_data(); Dtype* top_label = NULL; // suppress warnings about uninitialized variables if (this->output_labels_) { top_label = this->prefetch_label_.mutable_cpu_data(); } const int batch_size = this->layer_param_.data_param().batch_size(); for (int item_id = 0; item_id < batch_size; ++item_id) { // get a blob switch (this->layer_param_.data_param().backend()) { case DataParameter_DB_LEVELDB: CHECK(iter_); CHECK(iter_->Valid()); datum.ParseFromString(iter_->value().ToString()); break; case DataParameter_DB_LMDB: CHECK_EQ(mdb_cursor_get(mdb_cursor_, &mdb_key_, &mdb_value_, MDB_GET_CURRENT), MDB_SUCCESS); datum.ParseFromArray(mdb_value_.mv_data, mdb_value_.mv_size); break; default: LOG(FATAL) << "Unknown database backend"; } // Apply data transformations (mirror, scale, crop...) this->data_transformer_.Transform(item_id, datum, this->mean_, top_data); if (this->output_labels_) { // liu // top_label[item_id] = datum.label(); // LOG(ERROR) << "label size " << datum.label_size() << " " << datum.label(0) \ << " " << datum.label(1) << " " << datum.label(2) << " " << datum.label(3); for(int label_i=0; label_i < datum.label_size(); label_i++){ top_label[item_id * datum.label_size() + label_i] = datum.label(label_i); } } // go to the next iter switch (this->layer_param_.data_param().backend()) { case DataParameter_DB_LEVELDB: iter_->Next(); if (!iter_->Valid()) { // We have reached the end. Restart from the first. DLOG(INFO) << "Restarting data prefetching from start."; iter_->SeekToFirst(); } break; case DataParameter_DB_LMDB: if (mdb_cursor_get(mdb_cursor_, &mdb_key_, &mdb_value_, MDB_NEXT) != MDB_SUCCESS) { // We have reached the end. Restart from the first. DLOG(INFO) << "Restarting data prefetching from start."; CHECK_EQ(mdb_cursor_get(mdb_cursor_, &mdb_key_, &mdb_value_, MDB_FIRST), MDB_SUCCESS); } break; default: LOG(FATAL) << "Unknown database backend"; } } }
void DataLayer<Dtype>::DataLayerSetUp(const vector<Blob<Dtype>*>& bottom, vector<Blob<Dtype>*>* top) { // Initialize DB switch (this->layer_param_.data_param().backend()) { case DataParameter_DB_LEVELDB: { leveldb::DB* db_temp; leveldb::Options options = GetLevelDBOptions(); options.create_if_missing = false; LOG(INFO) << "Opening leveldb " << this->layer_param_.data_param().source(); leveldb::Status status = leveldb::DB::Open( options, this->layer_param_.data_param().source(), &db_temp); CHECK(status.ok()) << "Failed to open leveldb " << this->layer_param_.data_param().source() << std::endl << status.ToString(); db_.reset(db_temp); iter_.reset(db_->NewIterator(leveldb::ReadOptions())); iter_->SeekToFirst(); idx_ = 0; } break; case DataParameter_DB_LMDB: CHECK_EQ(mdb_env_create(&mdb_env_), MDB_SUCCESS) << "mdb_env_create failed"; CHECK_EQ(mdb_env_set_mapsize(mdb_env_, 1099511627776), MDB_SUCCESS); // 1TB CHECK_EQ(mdb_env_open(mdb_env_, this->layer_param_.data_param().source().c_str(), MDB_RDONLY|MDB_NOTLS, 0664), MDB_SUCCESS) << "mdb_env_open failed"; CHECK_EQ(mdb_txn_begin(mdb_env_, NULL, MDB_RDONLY, &mdb_txn_), MDB_SUCCESS) << "mdb_txn_begin failed"; CHECK_EQ(mdb_open(mdb_txn_, NULL, 0, &mdb_dbi_), MDB_SUCCESS) << "mdb_open failed"; CHECK_EQ(mdb_cursor_open(mdb_txn_, mdb_dbi_, &mdb_cursor_), MDB_SUCCESS) << "mdb_cursor_open failed"; LOG(INFO) << "Opening lmdb " << this->layer_param_.data_param().source(); CHECK_EQ(mdb_cursor_get(mdb_cursor_, &mdb_key_, &mdb_value_, MDB_FIRST), MDB_SUCCESS) << "mdb_cursor_get failed"; break; default: LOG(FATAL) << "Unknown database backend"; } // Check if we would need to randomly skip a few data points if (this->layer_param_.data_param().rand_skip()) { unsigned int skip = caffe_rng_rand() % this->layer_param_.data_param().rand_skip(); LOG(INFO) << "Skipping first " << skip << " data points."; while (skip-- > 0) { switch (this->layer_param_.data_param().backend()) { case DataParameter_DB_LEVELDB: iter_->Next(); idx_++; if (!iter_->Valid()) { iter_->SeekToFirst(); idx_ = 0; } break; case DataParameter_DB_LMDB: if (mdb_cursor_get(mdb_cursor_, &mdb_key_, &mdb_value_, MDB_NEXT) != MDB_SUCCESS) { CHECK_EQ(mdb_cursor_get(mdb_cursor_, &mdb_key_, &mdb_value_, MDB_FIRST), MDB_SUCCESS); } break; default: LOG(FATAL) << "Unknown database backend"; } } } // Read a data point, and use it to initialize the top blob. Datum datum; switch (this->layer_param_.data_param().backend()) { case DataParameter_DB_LEVELDB: datum.ParseFromString(iter_->value().ToString()); //LOG(INFO)<<idx_; break; case DataParameter_DB_LMDB: datum.ParseFromArray(mdb_value_.mv_data, mdb_value_.mv_size); break; default: LOG(FATAL) << "Unknown database backend"; } // image int crop_size = this->layer_param_.transform_param().crop_size(); if (crop_size > 0) { (*top)[0]->Reshape(this->layer_param_.data_param().batch_size(), datum.channels(), crop_size, crop_size); this->prefetch_data_.Reshape(this->layer_param_.data_param().batch_size(), datum.channels(), crop_size, crop_size); } else { (*top)[0]->Reshape( this->layer_param_.data_param().batch_size(), datum.channels(), datum.height(), datum.width()); this->prefetch_data_.Reshape(this->layer_param_.data_param().batch_size(), datum.channels(), datum.height(), datum.width()); } LOG(INFO) << "output data size: " << (*top)[0]->num() << "," << (*top)[0]->channels() << "," << (*top)[0]->height() << "," << (*top)[0]->width(); // label if (this->output_labels_) { (*top)[1]->Reshape(this->layer_param_.data_param().batch_size(), datum.label_size(), 1, 1); this->prefetch_label_.Reshape(this->layer_param_.data_param().batch_size(), datum.label_size(), 1, 1); } // datum size this->datum_channels_ = datum.channels(); this->datum_height_ = datum.height(); this->datum_width_ = datum.width(); this->datum_size_ = datum.channels() * datum.height() * datum.width(); }
void* PoseImageDataLayerPrefetch(void* layer_pointer) { CHECK(layer_pointer); PoseImageDataLayer<Dtype>* layer = reinterpret_cast<PoseImageDataLayer<Dtype>*>(layer_pointer); CHECK(layer); Datum datum; CHECK(layer->prefetch_data_); Dtype* top_data = layer->prefetch_data_->mutable_cpu_data(); Dtype* top_label = layer->prefetch_label_->mutable_cpu_data(); PoseImageDataParameter pose_image_data_param = layer->layer_param_.pose_image_data_param(); const Dtype scale = pose_image_data_param.scale(); const int batch_size = pose_image_data_param.batch_size(); const int crop_size = pose_image_data_param.crop_size(); const bool mirror = pose_image_data_param.mirror(); const int new_height = pose_image_data_param.new_height(); const int new_width = pose_image_data_param.new_width(); const int out_height = pose_image_data_param.out_height(); const int out_width = pose_image_data_param.out_width(); const int key_point_range = pose_image_data_param.key_point_range(); const float scale_lower_bound = pose_image_data_param.scale_lower_bound(); const float scale_upper_bound = pose_image_data_param.scale_upper_bound(); const int key_point_num = pose_image_data_param.key_point_num(); const int randmargin = pose_image_data_param.randmargin(); const int use_mode = pose_image_data_param.use_mode(); const float torso_ratio = pose_image_data_param.torso_ratio(); const int mx1 = pose_image_data_param.mx1(); const int mx2 = pose_image_data_param.mx2(); const int my1 = pose_image_data_param.my1(); const int my2 = pose_image_data_param.my2(); const bool color_aug = pose_image_data_param.color_aug(); if (mirror && crop_size == 0) { LOG(FATAL) << "Current implementation requires mirror and crop_size to be " << "set at the same time."; } // datum scales const int channels = layer->datum_channels_; const int height = layer->datum_height_; const int width = layer->datum_width_; const int size = layer->datum_size_; const int lines_size = layer->lines_.size(); const Dtype* mean = layer->data_mean_.cpu_data(); int * was = new int[out_height * out_width]; for (int item_id = 0; item_id < batch_size; ++item_id) { char ss1[1010],ss2[1010]; sprintf(ss1,"/home/dragon123/cnncode/showimg/%d.jpg",item_id); //sprintf(ss2,"/home/dragon123/cnncode/showimg/%d_gt.jpg",item_id); // get a blob float nowscale = 1; if (layer->phase_ == Caffe::TRAIN) nowscale = random(scale_lower_bound, scale_upper_bound); CHECK_GT(1.55, nowscale); CHECK_GT(nowscale, 0.95); CHECK_GT(lines_size, layer->lines_id_); if (use_mode == 1) { bool temp = PoseReadImageToDatum_mode1(layer->lines_[layer->lines_id_].first, layer->lines_[layer->lines_id_].second, new_height, new_width, &datum, nowscale, torso_ratio, mx1, mx2, my1, my2, randmargin); if (temp == false) continue; } else { bool temp = PoseReadImageToDatum_mode2(layer->lines_[layer->lines_id_].first, layer->lines_[layer->lines_id_].second, new_height, new_width, &datum, nowscale, torso_ratio, mx1, mx2, my1, my2, randmargin); if (temp == false) continue; } const string& data = datum.data(); if (new_height > 0 && new_width > 0) { CHECK(data.size()) << "Image cropping only support uint8 data"; int h_off, w_off; // We only do random crop when we do training. h_off = 0; w_off = 0; if (mirror && layer->PrefetchRand() % 2) { // Copy mirrored version for (int c = 0; c < channels; ++c) { float thisRand = 1; if(color_aug) { thisRand = random(0.8,1.2); } for (int h = 0; h < new_height; ++h) { for (int w = 0; w < new_width; ++w) { int top_index = ((item_id * channels + c) * new_height + h) * new_width + (new_width - 1 - w); int data_index = (c * height + h + h_off) * width + w + w_off; Dtype datum_element = static_cast<Dtype>(static_cast<uint8_t>(data[data_index])); top_data[top_index] = (datum_element - mean[data_index]) * scale; top_data[top_index] = min(top_data[top_index] * thisRand, (Dtype)(255.0)); } } } } else { // Normal copy //Mat img(Size(new_width,new_height), CV_8UC3); for (int c = 0; c < channels; ++c) { float thisRand = 1; if(color_aug) { thisRand = random(0.8,1.2); } for (int h = 0; h < new_height; ++h) { for (int w = 0; w < new_width; ++w) { int top_index = ((item_id * channels + c) * new_height + h) * new_width + w; int data_index = (c * height + h + h_off) * width + w + w_off; Dtype datum_element = static_cast<Dtype>(static_cast<uint8_t>(data[data_index])); top_data[top_index] = (datum_element - mean[data_index]) * scale; //img.at<cv::Vec3b>(h, w)[c] = (uchar)(datum_element * scale) * thisRand; top_data[top_index] = min(top_data[top_index] * thisRand, (Dtype)(255.0)); } } } //imwrite(ss1, img); } } else { // Just copy the whole data if (data.size()) { for (int j = 0; j < size; ++j) { Dtype datum_element = static_cast<Dtype>(static_cast<uint8_t>(data[j])); top_data[item_id * size + j] = (datum_element - mean[j]) * scale; } } else { for (int j = 0; j < size; ++j) { top_data[item_id * size + j] = (datum.float_data(j) - mean[j]) * scale; } } } float lblratio = new_height / out_height; vector<int> pts; for (int label_i = 0; label_i < datum.label_size(); label_i++) { pts.push_back( datum.label(label_i) / lblratio ); } int lblLen = key_point_num * out_height * out_width; PoseReadLabel(pts, was, top_label + item_id * lblLen, out_height, out_width); /*for(int ci = 0; ci < key_point_num; ci ++) { Mat img(Size(out_height, out_width), CV_8UC3); sprintf(ss2,"/home/dragon123/cnncode/showimg/%d_%d_gt.jpg",item_id, ci); for(int h = 0; h < out_height; h ++) for(int w = 0; w < out_width; w ++) { int clr = top_label[item_id * lblLen + ci * out_height * out_width + h * out_width + w]; if(clr <= 0) { if(clr == 0) for(int c = 0; c < 3; c ++) img.at<cv::Vec3b>(h, w)[c] = 0; if(clr < 0) for(int c = 0; c < 3; c ++) img.at<cv::Vec3b>(h, w)[c] = 128; } else { for(int c = 0; c < 3; c ++) img.at<cv::Vec3b>(h, w)[c] = 255; } } imwrite(ss2, img); }*/ // go to the next iter layer->lines_id_++; if (layer->lines_id_ >= lines_size) { // We have reached the end. Restart from the first. DLOG(INFO) << "Restarting data prefetching from start."; layer->lines_id_ = 0; if (layer->layer_param_.pose_image_data_param().shuffle()) { layer->ShuffleImages(); } } } delete was; return reinterpret_cast<void*>(NULL); }
void* ImageDataLayerPrefetch(void* layer_pointer) { CHECK(layer_pointer); ImageDataLayer<Dtype>* layer = reinterpret_cast<ImageDataLayer<Dtype>*>(layer_pointer); CHECK(layer); Datum datum; CHECK(layer->prefetch_data_); Dtype* top_data = layer->prefetch_data_->mutable_cpu_data(); Dtype* top_label = layer->prefetch_label_->mutable_cpu_data(); ImageDataParameter image_data_param = layer->layer_param_.image_data_param(); const Dtype scale = image_data_param.scale(); const int batch_size = image_data_param.batch_size(); const int crop_size = image_data_param.crop_size(); const bool mirror = image_data_param.mirror(); const int new_height = image_data_param.new_height(); const int new_width = image_data_param.new_width(); if (mirror && crop_size == 0) { LOG(FATAL) << "Current implementation requires mirror and crop_size to be " << "set at the same time."; } // datum scales const int channels = layer->datum_channels_; const int height = layer->datum_height_; const int width = layer->datum_width_; const int size = layer->datum_size_; const int lines_size = layer->lines_.size(); const Dtype* mean = layer->data_mean_.cpu_data(); for (int item_id = 0; item_id < batch_size; ++item_id) { // get a blob CHECK_GT(lines_size, layer->lines_id_); if (!ReadImageToDatum(layer->lines_[layer->lines_id_].first, layer->lines_[layer->lines_id_].second, new_height, new_width, &datum)) { continue; } const string& data = datum.data(); if (crop_size) { CHECK(data.size()) << "Image cropping only support uint8 data"; int h_off, w_off; // We only do random crop when we do training. if (false && layer->phase_ == Caffe::TRAIN) { h_off = layer->PrefetchRand() % (height - crop_size); w_off = layer->PrefetchRand() % (width - crop_size); } else { h_off = (height - crop_size) / 2; w_off = (width - crop_size) / 2; } if (mirror && layer->PrefetchRand() % 2) { // Copy mirrored version for (int c = 0; c < channels; ++c) { for (int h = 0; h < crop_size; ++h) { for (int w = 0; w < crop_size; ++w) { int top_index = ((item_id * channels + c) * crop_size + h) * crop_size + (crop_size - 1 - w); int data_index = (c * height + h + h_off) * width + w + w_off; Dtype datum_element = static_cast<Dtype>(static_cast<uint8_t>(data[data_index])); top_data[top_index] = (datum_element - mean[data_index]) * scale; } } } } else { // Normal copy for (int c = 0; c < channels; ++c) { for (int h = 0; h < crop_size; ++h) { for (int w = 0; w < crop_size; ++w) { int top_index = ((item_id * channels + c) * crop_size + h) * crop_size + w; int data_index = (c * height + h + h_off) * width + w + w_off; Dtype datum_element = static_cast<Dtype>(static_cast<uint8_t>(data[data_index])); top_data[top_index] = (datum_element - mean[data_index]) * scale; } } } } } else { // Just copy the whole data if (data.size()) { for (int j = 0; j < size; ++j) { Dtype datum_element = static_cast<Dtype>(static_cast<uint8_t>(data[j])); top_data[item_id * size + j] = (datum_element - mean[j]) * scale; } } else { for (int j = 0; j < size; ++j) { top_data[item_id * size + j] = (datum.float_data(j) - mean[j]) * scale; } } } //top_label[item_id] = datum.label(); for (int label_i = 0; label_i < datum.label_size(); label_i++) { top_label[item_id * datum.label_size() + label_i] = datum.label(label_i); } // go to the next iter layer->lines_id_++; if (layer->lines_id_ >= lines_size) { // We have reached the end. Restart from the first. DLOG(INFO) << "Restarting data prefetching from start."; layer->lines_id_ = 0; if (layer->layer_param_.image_data_param().shuffle()) { layer->ShuffleImages(); } } } return reinterpret_cast<void*>(NULL); }
void* DataLayerPrefetch(void* layer_pointer) { CHECK(layer_pointer); DataLayer<Dtype>* layer = static_cast<DataLayer<Dtype>*>(layer_pointer); CHECK(layer); Datum datum; CHECK(layer->prefetch_data_); Dtype* top_data = layer->prefetch_data_->mutable_cpu_data(); //数据 Dtype* top_label; //标签 if (layer->output_labels_) { top_label = layer->prefetch_label_->mutable_cpu_data(); } const Dtype scale = layer->layer_param_.data_param().scale(); const int batch_size = layer->layer_param_.data_param().batch_size(); const int crop_size = layer->layer_param_.data_param().crop_size(); const bool mirror = layer->layer_param_.data_param().mirror(); if (mirror && crop_size == 0) {//当前实现需要同时设置mirror和cropsize LOG(FATAL) << "Current implementation requires mirror and crop_size to be " << "set at the same time."; } // datum scales const int channels = layer->datum_channels_; const int height = layer->datum_height_; const int width = layer->datum_width_; const int size = layer->datum_size_; const Dtype* mean = layer->data_mean_.cpu_data(); for (int item_id = 0; item_id < batch_size; ++item_id) { //每一批数据的数量是batchsize,一个循环拉取一张 // get a blob CHECK(layer->iter_); CHECK(layer->iter_->Valid()); datum.ParseFromString(layer->iter_->value().ToString());//利用迭代器拉取下一批数据 const string& data = datum.data(); int label_blob_channels = layer->prefetch_label_->channels(); int label_data_dim = datum.label_size(); CHECK_EQ(layer->prefetch_label_->channels(), datum.label_size()) << "label size is NOT the same."; if (crop_size) {//如果需要裁剪 CHECK(data.size()) << "Image cropping only support uint8 data"; int h_off, w_off; // We only do random crop when we do training. //只是在训练阶段做随机裁剪 if (layer->phase_ == Caffe::TRAIN) { h_off = layer->PrefetchRand() % (height - crop_size); w_off = layer->PrefetchRand() % (width - crop_size); } else {//测试阶段固定裁剪 h_off = (height - crop_size) / 2; w_off = (width - crop_size) / 2; } //怎么感觉下面两种情况的代码是一样的? if (mirror && layer->PrefetchRand() % 2) { // Copy mirrored version for (int c = 0; c < channels; ++c) { for (int h = 0; h < crop_size; ++h) { for (int w = 0; w < crop_size; ++w) { int top_index = ((item_id * channels + c) * crop_size + h) * crop_size + (crop_size - 1 - w); int data_index = (c * height + h + h_off) * width + w + w_off; Dtype datum_element = static_cast<Dtype>(static_cast<uint8_t>(data[data_index])); top_data[top_index] = (datum_element - mean[data_index]) * scale; } } } } else {//如果不需要裁剪 // Normal copy //我们优先考虑data(),然后float_data() for (int c = 0; c < channels; ++c) { for (int h = 0; h < crop_size; ++h) { for (int w = 0; w < crop_size; ++w) { int top_index = ((item_id * channels + c) * crop_size + h) * crop_size + w; int data_index = (c * height + h + h_off) * width + w + w_off; Dtype datum_element = static_cast<Dtype>(static_cast<uint8_t>(data[data_index])); top_data[top_index] = (datum_element - mean[data_index]) * scale; } } } } } else { // we will prefer to use data() first, and then try float_data() if (data.size()) { for (int j = 0; j < size; ++j) { Dtype datum_element = static_cast<Dtype>(static_cast<uint8_t>(data[j])); top_data[item_id * size + j] = (datum_element - mean[j]) * scale; } } else { for (int j = 0; j < size; ++j) { top_data[item_id * size + j] = (datum.float_data(j) - mean[j]) * scale; } } } if (g_item_id++ < 5) { int label_size = datum.label_size(); int image_label = 0; for (int j = 0; j < label_size; ++j) { if (datum.label(j) == 1) { image_label = j; break; } } char strImgRawDataFile[255] = ""; sprintf(strImgRawDataFile, "caffe_%s_%05d_%d%s", "train", item_id, image_label, ".txt"); ofstream fout_image_raw_data(strImgRawDataFile); for (int h = 0; h < height; ++h) { for (int w = 0; w < width; ++w) { int pixel_index = h * height + w; Dtype datum_element = static_cast<Dtype>(static_cast<uint8_t>(data[pixel_index])); char strHexByte[3] = ""; sprintf(strHexByte, "%02X", (unsigned char)datum_element); fout_image_raw_data<<" "<<strHexByte; } fout_image_raw_data<<endl; } fout_image_raw_data<<endl; for (int j = 0; j < label_size; ++j) { fout_image_raw_data<<datum.label(j); } fout_image_raw_data.close(); } if (layer->output_labels_) { int label_size = datum.label_size(); for (int j = 0; j < label_size; ++j) { top_label[item_id * label_size + j] = datum.label(j); } //top_label[item_id] = datum.label(); } // go to the next iter layer->iter_->Next(); if (!layer->iter_->Valid()) { // We have reached the end. Restart from the first. DLOG(INFO) << "Restarting data prefetching from start."; layer->iter_->SeekToFirst(); } } return static_cast<void*>(NULL); }
void DataLayer<Dtype>::SetUp(const vector<Blob<Dtype>*>& bottom, vector<Blob<Dtype>*>* top) { CHECK_EQ(bottom.size(), 0) << "Data Layer takes no input blobs."; CHECK_GE(top->size(), 1) << "Data Layer takes at least one blob as output."; CHECK_LE(top->size(), 2) << "Data Layer takes at most two blobs as output."; if (top->size() == 1) { output_labels_ = false; } else { output_labels_ = true; } // Initialize the leveldb leveldb::DB* db_temp; leveldb::Options options; options.create_if_missing = false; options.max_open_files = 100; LOG(INFO) << "Opening leveldb " << this->layer_param_.data_param().source(); leveldb::Status status = leveldb::DB::Open( options, this->layer_param_.data_param().source(), &db_temp); CHECK(status.ok()) << "Failed to open leveldb " << this->layer_param_.data_param().source() << std::endl << status.ToString(); db_.reset(db_temp); iter_.reset(db_->NewIterator(leveldb::ReadOptions()));//通过迭代器来操纵leveldb iter_->SeekToFirst(); // Check if we would need to randomly skip a few data points //是否要随机跳过一些数据 if (this->layer_param_.data_param().rand_skip()) { unsigned int skip = caffe_rng_rand() % this->layer_param_.data_param().rand_skip(); LOG(INFO) << "Skipping first " << skip << " data points."; while (skip-- > 0) { iter_->Next(); if (!iter_->Valid()) { iter_->SeekToFirst(); } } } // Read a data point, and use it to initialize the top blob. //读取一个数据点,用来初始化topblob。所谓初始化,只要是指reshape。 //可以观察到下面iter_调用调用next。所以这次读取只是用来读取出来channels等参数的,不作处理。 Datum datum; datum.ParseFromString(iter_->value().ToString());//利用迭代器读取第一个数据点 // image图像数据 int crop_size = this->layer_param_.data_param().crop_size();//裁剪大小 if (crop_size > 0) {//需要裁剪 (*top)[0]->Reshape(this->layer_param_.data_param().batch_size(), datum.channels(), crop_size, crop_size); prefetch_data_.reset(new Blob<Dtype>( this->layer_param_.data_param().batch_size(), datum.channels(), crop_size, crop_size)); } else {//不需要裁剪 (*top)[0]->Reshape( this->layer_param_.data_param().batch_size(), datum.channels(), datum.height(), datum.width()); prefetch_data_.reset(new Blob<Dtype>( this->layer_param_.data_param().batch_size(), datum.channels(), datum.height(), datum.width())); } LOG(INFO) << "output data size: " << (*top)[0]->num() << "," << (*top)[0]->channels() << "," << (*top)[0]->height() << "," << (*top)[0]->width(); /* // label标签数据 if (output_labels_) { (*top)[1]->Reshape(this->layer_param_.data_param().batch_size(), 1, 1, 1); prefetch_label_.reset( new Blob<Dtype>(this->layer_param_.data_param().batch_size(), 1, 1, 1)); } */ // label标签数据 if (output_labels_) { (*top)[1]->Reshape(this->layer_param_.data_param().batch_size(), datum.label_size(), 1, 1); prefetch_label_.reset( new Blob<Dtype>(this->layer_param_.data_param().batch_size(), datum.label_size(), 1, 1)); } // datum size datum_channels_ = datum.channels(); datum_height_ = datum.height(); datum_width_ = datum.width(); datum_size_ = datum.channels() * datum.height() * datum.width(); CHECK_GT(datum_height_, crop_size); CHECK_GT(datum_width_, crop_size); // check if we want to have mean 是否要减去均值 if (this->layer_param_.data_param().has_mean_file()) { const string& mean_file = this->layer_param_.data_param().mean_file(); LOG(INFO) << "Loading mean file from" << mean_file; BlobProto blob_proto; ReadProtoFromBinaryFileOrDie(mean_file.c_str(), &blob_proto); data_mean_.FromProto(blob_proto); CHECK_EQ(data_mean_.num(), 1); CHECK_EQ(data_mean_.channels(), datum_channels_); CHECK_EQ(data_mean_.height(), datum_height_); CHECK_EQ(data_mean_.width(), datum_width_); } else { // Simply initialize an all-empty mean. data_mean_.Reshape(1, datum_channels_, datum_height_, datum_width_); } // Now, start the prefetch thread. Before calling prefetch, we make two // cpu_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. prefetch_data_->mutable_cpu_data(); if (output_labels_) { prefetch_label_->mutable_cpu_data(); } data_mean_.cpu_data(); DLOG(INFO) << "Initializing prefetch"; CreatePrefetchThread(); DLOG(INFO) << "Prefetch initialized."; }