void DataTransformer<Dtype>::Transform(const cv::Mat& img,
Blob<Dtype>* transformed_blob) {
const int min_side = param_.min_side();
const int min_side_min = param_.min_side_min();
const int min_side_max = param_.min_side_max();
const int crop_size = param_.crop_size();
const int rotation_angle = param_.max_rotation_angle();
const float min_contrast = param_.min_contrast();
const float max_contrast = param_.max_contrast();
const int max_brightness_shift = param_.max_brightness_shift();
const float max_smooth = param_.max_smooth();
const int max_color_shift = param_.max_color_shift();
const float apply_prob = 1.f - param_.apply_probability();
const bool debug_params = param_.debug_params();
// Check dimensions.
const int channels = transformed_blob->channels();
const int height = transformed_blob->height();
const int width = transformed_blob->width();
const int num = transformed_blob->num();
const Dtype scale = param_.scale();
const bool has_mean_file = param_.has_mean_file();
const bool has_mean_values = mean_values_.size() > 0;
float current_prob;
const bool do_rotation = rotation_angle > 0 && phase_ == TRAIN;
const bool do_resize_to_min_side = min_side > 0;
const bool do_resize_to_min_side_min = min_side_min > 0;
const bool do_resize_to_min_side_max = min_side_max > 0;
const bool do_mirror = param_.mirror() && phase_ == TRAIN && Rand(2);
caffe_rng_uniform(1, 0.f, 1.f, ¤t_prob);
const bool do_brightness = param_.contrast_brightness_adjustment() && phase_ == TRAIN && current_prob > apply_prob;
caffe_rng_uniform(1, 0.f, 1.f, ¤t_prob);
const bool do_smooth = param_.smooth_filtering() && phase_ == TRAIN && max_smooth > 1 && current_prob > apply_prob;
caffe_rng_uniform(1, 0.f, 1.f, ¤t_prob);
const bool do_color_shift = max_color_shift > 0 && phase_ == TRAIN && current_prob > apply_prob;
cv::Mat cv_img = img;
int current_angle = 0;
if (do_rotation) {
current_angle = Rand(rotation_angle*2 + 1) - rotation_angle;
if (current_angle)
rotate(cv_img, current_angle);
}
// resizing and crop according to min side, preserving aspect ratio
if (do_resize_to_min_side) {
resize(cv_img, min_side);
//random_crop(cv_img, min_side);
}
if (do_resize_to_min_side_min && do_resize_to_min_side_max) {
//std::cout << min_side_min << " "<<min_side_max<<std::endl;
int min_side_length = min_side_min + Rand(min_side_max - min_side_min + 1);
resize(cv_img, min_side_length);
//crop_center(cv_img, min_side, min_side);
//random_crop(cv_img, min_side_length);
}
// apply color shift
if (do_color_shift) {
int b = Rand(max_color_shift + 1);
int g = Rand(max_color_shift + 1);
int r = Rand(max_color_shift + 1);
int sign = Rand(2);
cv::Mat shiftArr = cv_img.clone();
shiftArr.setTo(cv::Scalar(b,g,r));
if (sign == 1) {
cv_img -= shiftArr;
} else {
cv_img += shiftArr;
}
}
// set contrast and brightness
float alpha;
int beta;
if (do_brightness){
caffe_rng_uniform(1, min_contrast, max_contrast, &alpha);
beta = Rand(max_brightness_shift * 2 + 1) - max_brightness_shift;
cv_img.convertTo(cv_img, -1, alpha, beta);
}
// set smoothness
int smooth_param = 0;
int smooth_type = 0;
if (do_smooth) {
smooth_type = Rand(4);
smooth_param = 1 + 2 * Rand(max_smooth/2);
switch (smooth_type) {
case 0:
cv::GaussianBlur(cv_img, cv_img, cv::Size(smooth_param, smooth_param), 0);
break;
case 1:
cv::blur(cv_img, cv_img, cv::Size(smooth_param, smooth_param));
break;
case 2:
cv::medianBlur(cv_img, cv_img, smooth_param);
break;
case 3:
cv::boxFilter(cv_img, cv_img, -1, cv::Size(smooth_param * 2, smooth_param * 2));
break;
default:
break;
}
}
if (debug_params && phase_ == TRAIN) {
LOG(INFO) << "----------------------------------------";
if (do_rotation) {
LOG(INFO) << "* parameter for rotation: ";
LOG(INFO) << " current rotation angle: " << current_angle;
}
if (do_brightness) {
LOG(INFO) << "* parameter for contrast adjustment: ";
LOG(INFO) << " alpha: " << alpha << ", beta: " << beta;
}
if (do_smooth) {
LOG(INFO) << "* parameter for smooth filtering: ";
LOG(INFO) << " smooth type: " << smooth_type << ", smooth param: " << smooth_param;
}
}
const int img_channels = cv_img.channels();
const int img_height = cv_img.rows;
const int img_width = cv_img.cols;
CHECK_GT(img_channels, 0);
CHECK_GE(img_height, crop_size);
CHECK_GE(img_width, crop_size);
CHECK_EQ(channels, img_channels);
CHECK_LE(height, img_height);
CHECK_LE(width, img_width);
CHECK_GE(num, 1);
CHECK(cv_img.depth() == CV_8U) << "Image data type must be unsigned byte";
Dtype* mean = NULL;
if (has_mean_file) {
CHECK_EQ(img_channels, data_mean_.channels());
CHECK_EQ(img_height, data_mean_.height());
CHECK_EQ(img_width, data_mean_.width());
mean = data_mean_.mutable_cpu_data();
}
if (has_mean_values) {
CHECK(mean_values_.size() == 1 || mean_values_.size() == img_channels) <<
"Specify either 1 mean_value or as many as channels: " << img_channels;
if (img_channels > 1 && mean_values_.size() == 1) {
// Replicate the mean_value for simplicity
for (int c = 1; c < img_channels; ++c) {
mean_values_.push_back(mean_values_[0]);
}
}
}
int h_off = 0;
int w_off = 0;
cv::Mat cv_cropped_img = cv_img;
if (crop_size) {
CHECK_EQ(crop_size, height);
CHECK_EQ(crop_size, width);
// We only do random crop when we do training.
if (phase_ == TRAIN) {
h_off = Rand(img_height - crop_size + 1);
w_off = Rand(img_width - crop_size + 1);
} else {
h_off = (img_height - crop_size) / 2;
w_off = (img_width - crop_size) / 2;
}
cv::Rect roi(w_off, h_off, crop_size, crop_size);
cv_cropped_img = cv_img(roi);
} else {
//CHECK_EQ(img_height, height);
//CHECK_EQ(img_width, width);
}
CHECK(cv_cropped_img.data);
Dtype* transformed_data = transformed_blob->mutable_cpu_data();
int top_index;
for (int h = 0; h < height; ++h) {
const uchar* ptr = cv_cropped_img.ptr<uchar>(h);
int img_index = 0;
for (int w = 0; w < width; ++w) {
for (int c = 0; c < img_channels; ++c) {
if (do_mirror) {
top_index = (c * height + h) * width + (width - 1 - w);
} else {
top_index = (c * height + h) * width + w;
}
// int top_index = (c * height + h) * width + w;
Dtype pixel = static_cast<Dtype>(ptr[img_index++]);
if (has_mean_file) {
int mean_index = (c * img_height + h_off + h) * img_width + w_off + w;
transformed_data[top_index] =
(pixel - mean[mean_index]) * scale;
} else {
if (has_mean_values) {
transformed_data[top_index] =
(pixel - mean_values_[c]) * scale;
} else {
transformed_data[top_index] = pixel * scale;
}
}
}
}
}
}
cv::Mat converttoopencvimg<float>( float* singleimage, int height, int width ) {
cv::Mat cv_img(height, width, CV_32FC3, singleimage);
return cv_img;
}
cv::Mat converttoopencvimg<double>( double* singleimage, int height, int width ) {
cv::Mat cv_img(height, width, CV_64FC3, singleimage);
return cv_img;
}
void DenseImageDataLayer<Dtype>::InternalThreadEntry() {
CPUTimer batch_timer;
batch_timer.Start();
double read_time = 0;
double trans_time = 0;
CPUTimer timer;
CHECK(this->prefetch_data_.count());
CHECK(this->transformed_data_.count());
DenseImageDataParameter dense_image_data_param = this->layer_param_.dense_image_data_param();
const int batch_size = dense_image_data_param.batch_size();
const int new_height = dense_image_data_param.new_height();
const int new_width = dense_image_data_param.new_width();
const int crop_height = dense_image_data_param.crop_height();
const int crop_width = dense_image_data_param.crop_width();
const int crop_size = this->layer_param_.transform_param().crop_size();
const bool is_color = dense_image_data_param.is_color();
string root_folder = dense_image_data_param.root_folder();
// Reshape on single input batches for inputs of varying dimension.
if (batch_size == 1 && crop_size == 0 && new_height == 0 && new_width == 0 && crop_height == 0 && crop_width == 0) {
cv::Mat cv_img = ReadImageToCVMat(root_folder + lines_[lines_id_].first,
0, 0, is_color);
this->prefetch_data_.Reshape(1, cv_img.channels(),
cv_img.rows, cv_img.cols);
this->transformed_data_.Reshape(1, cv_img.channels(),
cv_img.rows, cv_img.cols);
this->prefetch_label_.Reshape(1, 1, cv_img.rows, cv_img.cols);
this->transformed_label_.Reshape(1, 1, cv_img.rows, cv_img.cols);
}
Dtype* prefetch_data = this->prefetch_data_.mutable_cpu_data();
Dtype* prefetch_label = this->prefetch_label_.mutable_cpu_data();
// datum scales
const int lines_size = lines_.size();
for (int item_id = 0; item_id < batch_size; ++item_id) {
// get a blob
timer.Start();
CHECK_GT(lines_size, lines_id_);
cv::Mat cv_img = ReadImageToCVMat(root_folder + lines_[lines_id_].first,
new_height, new_width, is_color);
CHECK(cv_img.data) << "Could not load " << lines_[lines_id_].first;
cv::Mat cv_lab = ReadImageToCVMat(root_folder + lines_[lines_id_].second,
new_height, new_width, false, true);
CHECK(cv_lab.data) << "Could not load " << lines_[lines_id_].second;
read_time += timer.MicroSeconds();
timer.Start();
// Apply random horizontal mirror of images
if (this->layer_param_.dense_image_data_param().mirror()) {
const bool do_mirror = caffe_rng_rand() % 2;
if (do_mirror) {
cv::flip(cv_img,cv_img,1);
cv::flip(cv_lab,cv_lab,1);
}
}
// Apply crop
int height = cv_img.rows;
int width = cv_img.cols;
int h_off = 0;
int w_off = 0;
if (crop_height>0 && crop_width>0) {
h_off = caffe_rng_rand() % (height - crop_height + 1);
w_off = caffe_rng_rand() % (width - crop_width + 1);
cv::Rect myROI(w_off, h_off, crop_width, crop_height);
cv_img = cv_img(myROI);
cv_lab = cv_lab(myROI);
}
// Apply transformations (mirror, crop...) to the image
int offset = this->prefetch_data_.offset(item_id);
this->transformed_data_.set_cpu_data(prefetch_data + offset);
this->data_transformer_->Transform(cv_img, &(this->transformed_data_));
// transform label the same way
int label_offset = this->prefetch_label_.offset(item_id);
this->transformed_label_.set_cpu_data(prefetch_label + label_offset);
this->data_transformer_->Transform(cv_lab, &this->transformed_label_, true);
CHECK(!this->layer_param_.transform_param().mirror() &&
this->layer_param_.transform_param().crop_size() == 0)
<< "FIXME: Any stochastic transformation will break layer due to "
<< "the need to transform input and label images in the same way";
trans_time += timer.MicroSeconds();
// go to the next iter
lines_id_++;
if (lines_id_ >= lines_size) {
// We have reached the end. Restart from the first.
DLOG(INFO) << "Restarting data prefetching from start.";
lines_id_ = 0;
if (this->layer_param_.dense_image_data_param().shuffle()) {
ShuffleImages();
}
}
}
batch_timer.Stop();
DLOG(INFO) << "Prefetch batch: " << batch_timer.MilliSeconds() << " ms.";
DLOG(INFO) << " Read time: " << read_time / 1000 << " ms.";
DLOG(INFO) << "Transform time: " << trans_time / 1000 << " ms.";
}
