void* VideoDataLayerPrefetch(void* layer_pointer) {
CHECK(layer_pointer);
VideoDataLayer<Dtype>* layer = static_cast<VideoDataLayer<Dtype>*>(layer_pointer);
CHECK(layer);
VolumeDatum datum;
CHECK(layer->prefetch_data_);
Dtype* top_data = layer->prefetch_data_->mutable_cpu_data();
Dtype* top_label;
if (layer->output_labels_) {
top_label = layer->prefetch_label_->mutable_cpu_data();
}
const Dtype scale = layer->layer_param_.image_data_param().scale();
const int batch_size = layer->layer_param_.image_data_param().batch_size();
const int crop_size = layer->layer_param_.image_data_param().crop_size();
const bool mirror = layer->layer_param_.image_data_param().mirror();
const int new_length = layer->layer_param_.image_data_param().new_length();
const int new_height = layer->layer_param_.image_data_param().new_height();
const int new_width = layer->layer_param_.image_data_param().new_width();
const bool use_image = layer->layer_param_.image_data_param().use_image();
const int sampling_rate = layer->layer_param_.image_data_param().sampling_rate();
const bool use_temporal_jitter = layer->layer_param_.image_data_param().use_temporal_jitter();
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 length = layer->datum_length_;
const int height = layer->datum_height_;
const int width = layer->datum_width_;
const int size = layer->datum_size_;
const int chunks_size = layer->shuffle_index_.size();
const Dtype* mean = layer->data_mean_.cpu_data();
const int show_data = layer->layer_param_.image_data_param().show_data();
char *data_buffer;
if (show_data)
data_buffer = new char[size];
for (int item_id = 0; item_id < batch_size; ++item_id) {
// get a blob
CHECK_GT(chunks_size, layer->lines_id_);
bool read_status;
int id = layer->shuffle_index_[layer->lines_id_];
if (!use_image){
if (!use_temporal_jitter){
read_status = ReadVideoToVolumeDatum(layer->file_list_[id].c_str(), layer->start_frm_list_[id],
layer->label_list_[id], new_length, new_height, new_width, sampling_rate, &datum);
}else{
read_status = ReadVideoToVolumeDatum(layer->file_list_[id].c_str(), -1,
layer->label_list_[id], new_length, new_height, new_width, sampling_rate, &datum);
}
}
else {
if (!use_temporal_jitter) {
read_status = ReadImageSequenceToVolumeDatum(layer->file_list_[id].c_str(), layer->start_frm_list_[id],
layer->label_list_[id], new_length, new_height, new_width, layer->individual_sampling_rate_list_[id], &datum); // 090515
} else {
int num_of_frames = layer->start_frm_list_[id];
int use_start_frame;
if (num_of_frames<new_length*sampling_rate){
LOG(INFO) << "not enough frames; having " << num_of_frames;
read_status = false;
} else {
if (layer->phase_ == Caffe::TRAIN)
use_start_frame = layer->PrefetchRand()%(num_of_frames-new_length*sampling_rate+1)+1;
else
use_start_frame = 0;
read_status = ReadImageSequenceToVolumeDatum(layer->file_list_[id].c_str(), use_start_frame,
layer->label_list_[id], new_length, new_height, new_width, layer->individual_sampling_rate_list_[id], &datum); // 090515
}
}
}
if (layer->phase_ == Caffe::TEST){
CHECK(read_status) << "Testing must not miss any example";
}
if (!read_status) {
//LOG(ERROR) << "cannot read " << layer->file_list_[id];
layer->lines_id_++;
if (layer->lines_id_ >= chunks_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()){
std::random_shuffle(layer->shuffle_index_.begin(), layer->shuffle_index_.end());
}
}
item_id--;
continue;
}
//LOG(INFO) << "--> " << item_id;
//LOG(INFO) << "label " << datum.label();
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 (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 l = 0; l < length; ++l) {
for (int h = 0; h < crop_size; ++h) {
for (int w = 0; w < crop_size; ++w) {
int top_index = (((item_id * channels + c) * length + l) * crop_size + h)
* crop_size + (crop_size - 1 - w);
int data_index = ((c * length + l) * 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;
if (show_data)
data_buffer[((c * length + l) * crop_size + h)
* crop_size + (crop_size - 1 - w)] = static_cast<uint8_t>(data[data_index]);
}
}
}
}
} else {
// Normal copy
for (int c = 0; c < channels; ++c) {
for (int l = 0; l < length; ++l) {
for (int h = 0; h < crop_size; ++h) {
for (int w = 0; w < crop_size; ++w) {
int top_index = (((item_id * channels + c) * length + l) * crop_size + h)
* crop_size + w;
int data_index = ((c * length + l) * 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;
if (show_data)
data_buffer[((c * length + l) * crop_size + h)
* crop_size + w] = static_cast<uint8_t>(data[data_index]);
}
}
}
}
}
} 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;
if (show_data)
data_buffer[j] = static_cast<uint8_t>(data[j]);
}
} else {
for (int j = 0; j < size; ++j) {
top_data[item_id * size + j] =
(datum.float_data(j) - mean[j]) * scale;
}
}
}
if (show_data>0){
int image_size, channel_size;
if (crop_size){
image_size = crop_size * crop_size;
}else{
image_size = height * width;
}
channel_size = length * image_size;
for (int l = 0; l < length; ++l) {
for (int c = 0; c < channels; ++c) {
cv::Mat img;
char ch_name[64];
if (crop_size)
BufferToGrayImage(data_buffer + c * channel_size + l * image_size, crop_size, crop_size, &img);
else
BufferToGrayImage(data_buffer + c * channel_size + l * image_size, height, width, &img);
sprintf(ch_name, "Channel %d", c);
cv::namedWindow(ch_name, CV_WINDOW_AUTOSIZE);
cv::imshow( ch_name, img);
}
cv::waitKey(100);
}
}
if (layer->output_labels_) {
top_label[item_id] = datum.label();
// LOG(INFO) << "fetching label" << datum.label() << std::endl;
}
layer->lines_id_++;
if (layer->lines_id_ >= chunks_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()){
std::random_shuffle(layer->shuffle_index_.begin(), layer->shuffle_index_.end());
}
}
}
if (show_data & data_buffer!=NULL)
delete []data_buffer;
return static_cast<void*>(NULL);
}
int main(int argc, char** argv) {
::google::InitGoogleLogging(argv[0]);
if (argc != 3) {
LOG(ERROR) << "Usage: compute_image_mean input_leveldb output_file";
return 1;
}
leveldb::DB* db;
leveldb::Options options;
options.create_if_missing = false;
LOG(INFO) << "Opening leveldb " << argv[1];
leveldb::Status status = leveldb::DB::Open(
options, argv[1], &db);
CHECK(status.ok()) << "Failed to open leveldb " << argv[1];
leveldb::ReadOptions read_options;
read_options.fill_cache = false;
leveldb::Iterator* it = db->NewIterator(read_options);
it->SeekToFirst();
VolumeDatum datum;
BlobProto sum_blob;
int count = 0;
datum.ParseFromString(it->value().ToString());
sum_blob.set_num(1);
sum_blob.set_channels(datum.channels());
sum_blob.set_length(datum.length());
sum_blob.set_height(datum.height());
sum_blob.set_width(datum.width());
const int data_size = datum.channels() * datum.length() * datum.height() * datum.width();
int size_in_datum = std::max<int>(datum.data().size(),
datum.float_data_size());
for (int i = 0; i < size_in_datum; ++i) {
sum_blob.add_data(0.);
}
LOG(INFO) << "Starting Iteration";
for (it->SeekToFirst(); it->Valid(); it->Next()) {
// just a dummy operation
datum.ParseFromString(it->value().ToString());
const string& data = datum.data();
size_in_datum = std::max<int>(datum.data().size(), datum.float_data_size());
CHECK_EQ(size_in_datum, data_size) << "Incorrect data field size " <<
size_in_datum;
if (data.size() != 0) {
for (int i = 0; i < size_in_datum; ++i) {
sum_blob.set_data(i, sum_blob.data(i) + (uint8_t)data[i]);
}
} else {
for (int i = 0; i < size_in_datum; ++i) {
sum_blob.set_data(i, sum_blob.data(i) +
static_cast<float>(datum.float_data(i)));
}
}
++count;
if (count % 10000 == 0) {
LOG(ERROR) << "Processed " << count << " files.";
}
}
if (count % 10000 != 0) {
LOG(ERROR) << "Processed " << count << " files.";
}
for (int i = 0; i < sum_blob.data_size(); ++i) {
sum_blob.set_data(i, sum_blob.data(i) / count);
}
// Write to disk
LOG(INFO) << "Write to " << argv[2];
WriteProtoToBinaryFile(sum_blob, argv[2]);
delete db;
return 0;
}
void* VolumeDataLayerPrefetch(void* layer_pointer) {
CHECK(layer_pointer);
VolumeDataLayer<Dtype>* layer = static_cast<VolumeDataLayer<Dtype>*>(layer_pointer);
CHECK(layer);
VolumeDatum datum;
CHECK(layer->prefetch_data_);
Dtype* top_data = layer->prefetch_data_->mutable_cpu_data();
Dtype* top_label;
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) {
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 length = layer->datum_length_;
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();
const int show_data = layer->layer_param_.data_param().show_data();
char *data_buffer;
if (show_data)
data_buffer = new char[size];
for (int item_id = 0; item_id < batch_size; ++item_id) {
// get a blob
CHECK(layer->iter_);
CHECK(layer->iter_->Valid());
datum.ParseFromString(layer->iter_->value().ToString());
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 (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 l = 0; l < length; ++l) {
for (int h = 0; h < crop_size; ++h) {
for (int w = 0; w < crop_size; ++w) {
int top_index = (((item_id * channels + c) * length + l) * crop_size + h)
* crop_size + (crop_size - 1 - w);
int data_index = ((c * length + l) * 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;
if (show_data)
data_buffer[((c * length + l) * crop_size + h)
* crop_size + (crop_size - 1 - w)] = static_cast<uint8_t>(data[data_index]);
}
}
}
}
} else {
// Normal copy
for (int c = 0; c < channels; ++c) {
for (int l = 0; l < length; ++l) {
for (int h = 0; h < crop_size; ++h) {
for (int w = 0; w < crop_size; ++w) {
int top_index = (((item_id * channels + c) * length + l) * crop_size + h)
* crop_size + w;
int data_index = ((c * length + l) * 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;
if (show_data)
data_buffer[((c * length + l) * crop_size + h)
* crop_size + w] = static_cast<uint8_t>(data[data_index]);
}
}
}
}
}
} 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;
if (show_data)
data_buffer[j] = static_cast<uint8_t>(data[j]);
}
} else {
for (int j = 0; j < size; ++j) {
top_data[item_id * size + j] =
(datum.float_data(j) - mean[j]) * scale;
}
}
}
if (show_data>0){
int image_size, channel_size;
if (crop_size){
image_size = crop_size * crop_size;
}else{
image_size = height * width;
}
channel_size = length * image_size;
for (int l = 0; l < length; ++l) {
for (int c = 0; c < channels; ++c) {
cv::Mat img;
char ch_name[64];
if (crop_size)
BufferToGrayImage(data_buffer + c * channel_size + l * image_size, crop_size, crop_size, &img);
else
BufferToGrayImage(data_buffer + c * channel_size + l * image_size, height, width, &img);
sprintf(ch_name, "Channel %d", c);
cv::namedWindow(ch_name, CV_WINDOW_AUTOSIZE);
cv::imshow( ch_name, img);
}
cv::waitKey(100);
}
}
if (layer->output_labels_) {
top_label[item_id] = datum.label();
}
// go to the next iteration
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();
}
}
if (show_data & data_buffer!=NULL)
delete []data_buffer;
return static_cast<void*>(NULL);
}