void Im2colLayer<Dtype>::LayerSetUp(const vector<Blob<Dtype>*>& bottom,
const vector<Blob<Dtype>*>& top) {
ConvolutionParameter conv_param = this->layer_param_.convolution_param();
force_nd_im2col_ = conv_param.force_nd_im2col();
const int input_num_dims = bottom[0]->shape().size();
channel_axis_ = bottom[0]->CanonicalAxisIndex(conv_param.axis());
const int first_spatial_dim = channel_axis_ + 1;
num_spatial_axes_ = input_num_dims - first_spatial_dim;
CHECK_GE(num_spatial_axes_, 1);
vector<int> dim_blob_shape(1, num_spatial_axes_);
// Setup filter kernel dimensions (kernel_shape_).
kernel_shape_.Reshape(dim_blob_shape);
int* kernel_shape_data = kernel_shape_.mutable_cpu_data();
if (conv_param.has_kernel_h() || conv_param.has_kernel_w()) {
CHECK_EQ(num_spatial_axes_, 2)
<< "kernel_h & kernel_w can only be used for 2D convolution.";
CHECK_EQ(0, conv_param.kernel_size_size())
<< "Either kernel_size or kernel_h/w should be specified; not both.";
kernel_shape_data[0] = conv_param.kernel_h();
kernel_shape_data[1] = conv_param.kernel_w();
} else {
const int num_kernel_dims = conv_param.kernel_size_size();
CHECK(num_kernel_dims == 1 || num_kernel_dims == num_spatial_axes_)
<< "kernel_size must be specified once, or once per spatial dimension "
<< "(kernel_size specified " << num_kernel_dims << " times; "
<< num_spatial_axes_ << " spatial dims);";
for (int i = 0; i < num_spatial_axes_; ++i) {
kernel_shape_data[i] =
conv_param.kernel_size((num_kernel_dims == 1) ? 0 : i);
}
}
for (int i = 0; i < num_spatial_axes_; ++i) {
CHECK_GT(kernel_shape_data[i], 0) << "Filter dimensions must be nonzero.";
}
// Setup stride dimensions (stride_).
stride_.Reshape(dim_blob_shape);
int* stride_data = stride_.mutable_cpu_data();
if (conv_param.has_stride_h() || conv_param.has_stride_w()) {
CHECK_EQ(num_spatial_axes_, 2)
<< "stride_h & stride_w can only be used for 2D convolution.";
CHECK_EQ(0, conv_param.stride_size())
<< "Either stride or stride_h/w should be specified; not both.";
stride_data[0] = conv_param.stride_h();
stride_data[1] = conv_param.stride_w();
} else {
const int num_stride_dims = conv_param.stride_size();
CHECK(num_stride_dims == 0 || num_stride_dims == 1 ||
num_stride_dims == num_spatial_axes_)
<< "stride must be specified once, or once per spatial dimension "
<< "(stride specified " << num_stride_dims << " times; "
<< num_spatial_axes_ << " spatial dims);";
const int kDefaultStride = 1;
for (int i = 0; i < num_spatial_axes_; ++i) {
stride_data[i] = (num_stride_dims == 0) ? kDefaultStride :
conv_param.stride((num_stride_dims == 1) ? 0 : i);
CHECK_GT(stride_data[i], 0) << "Stride dimensions must be nonzero.";
}
}
// Setup pad dimensions (pad_).
pad_.Reshape(dim_blob_shape);
int* pad_data = pad_.mutable_cpu_data();
if (conv_param.has_pad_h() || conv_param.has_pad_w()) {
CHECK_EQ(num_spatial_axes_, 2)
<< "pad_h & pad_w can only be used for 2D convolution.";
CHECK_EQ(0, conv_param.pad_size())
<< "Either pad or pad_h/w should be specified; not both.";
pad_data[0] = conv_param.pad_h();
pad_data[1] = conv_param.pad_w();
} else {
const int num_pad_dims = conv_param.pad_size();
CHECK(num_pad_dims == 0 || num_pad_dims == 1 ||
num_pad_dims == num_spatial_axes_)
<< "pad must be specified once, or once per spatial dimension "
<< "(pad specified " << num_pad_dims << " times; "
<< num_spatial_axes_ << " spatial dims);";
const int kDefaultPad = 0;
for (int i = 0; i < num_spatial_axes_; ++i) {
pad_data[i] = (num_pad_dims == 0) ? kDefaultPad :
conv_param.pad((num_pad_dims == 1) ? 0 : i);
}
}
}
void CropLayer<Dtype>::LayerSetUp(const vector<Blob<Dtype>*>& bottom,
const vector<Blob<Dtype>*>& top) {
// Calculate number of spatial axis
CropParameter crop_param = this->layer_param_.crop_param();
channel_axis_ = bottom[0]->CanonicalAxisIndex(crop_param.axis());
channels_ = bottom[0]->shape(channel_axis_);
const int first_spatial_axis = channel_axis_ + 1;
num_axes_ = bottom[0]->num_axes();
num_spatial_axes_ = num_axes_ - first_spatial_axis;
CHECK_GE(num_spatial_axes_, 1);
vector<int> dim_blob_shape(1, num_axes_);
// Construct a map from top blobs to layer inds, skipping over in-place
// connections.
CHECK(this->net_!=NULL) << "Crop Layer must be used in a net";
map<Blob<Dtype>*, int> down_map;
for (int layer_ind = 0; layer_ind < this->net_->top_vecs().size();
++layer_ind) {
vector<Blob<Dtype>*> tops = this->net_->top_vecs()[layer_ind];
for (int top_ind = 0; top_ind < tops.size(); ++top_ind) {
if (down_map.find(tops[top_ind]) == down_map.end()) {
down_map[tops[top_ind]] = layer_ind;
}
}
}
// Walk back from the first bottom, keeping track of all the blobs we pass.
set<Blob<Dtype>*> path_blobs;
Blob<Dtype>* blob = bottom[0];
int layer_ind;
// TODO this logic can be simplified if all blobs are tops
path_blobs.insert(blob);
while (down_map.find(blob) != down_map.end()) {
layer_ind = down_map[blob];
if (this->net_->bottom_vecs()[layer_ind].size() == 0) {
break;
}
blob = this->net_->bottom_vecs()[layer_ind][0];
path_blobs.insert(blob);
}
// Now walk back from the second bottom, until we find a blob of intersection.
Blob<Dtype>* inter_blob = bottom[1];
while (path_blobs.find(inter_blob) == path_blobs.end()) {
CHECK(down_map.find(inter_blob) != down_map.end())
<< "Cannot align apparently disconnected blobs.";
layer_ind = down_map[inter_blob];
CHECK_GT(this->net_->bottom_vecs()[layer_ind].size(), 0)
<< "Cannot align apparently disconnected blobs.";
inter_blob = this->net_->bottom_vecs()[layer_ind][0];
}
// Compute the coord map from the blob of intersection to each bottom.
vector<DiagonalAffineMap<Dtype> > coord_maps(2,
DiagonalAffineMap<Dtype>::identity(num_spatial_axes_));
for (int i = 0; i < 2; ++i) {
for (Blob<Dtype>* blob = bottom[i]; blob != inter_blob;
blob = this->net_->bottom_vecs()[down_map[blob]][0]) {
shared_ptr<Layer<Dtype> > layer = this->net_->layers()[down_map[blob]];
// printf("[%d] %s\n",i,layer->type());
coord_maps[i] = coord_maps[i].compose(layer->coord_map(num_spatial_axes_));
// printf("done [%d] %s\n",i,layer->type());
}
}
// Compute the mapping from first bottom coordinates to second.
crop_.Reshape(dim_blob_shape);
top_shape_.Reshape(dim_blob_shape);
bottom_shape_.Reshape(dim_blob_shape);
int* crop_data = crop_.mutable_cpu_data();
int* top_shape_data = top_shape_.mutable_cpu_data();
int* bottom_shape_data = bottom_shape_.mutable_cpu_data();
// printf("maps %d %d \n",coord_maps[0].size(), coord_maps[1].size());
DiagonalAffineMap<Dtype> crop_map =
coord_maps[1].compose(coord_maps[0].inv());
// printf("Done compute map \n");
// printf("num_axes_ %d \n",num_axes_);
caffe_set(num_axes_, static_cast<int>(0), crop_data);
for (int i = 0; i < num_spatial_axes_; ++i) {
// Check for scale mismatch (unfortunately, CHECK_DOUBLE_EQ does not
// support a message like the other CHECKs).
CHECK_DOUBLE_EQ(crop_map.coefs()[i].first, 1);
CHECK_LE(crop_map.coefs()[i].second, 0) << "Negative crop width.";
// Check that the crop width is an integer.
CHECK_DOUBLE_EQ(crop_map.coefs()[i].second,
round(crop_map.coefs()[i].second));
crop_data[first_spatial_axis+i] = - round(crop_map.coefs()[i].second);
}
// printf("shapes \n");
for (int i = 0; i < channel_axis_+1; ++i) {
bottom_shape_data[i] = bottom[0]->shape(i);
top_shape_data[i] = bottom[0]->shape(i);
}
// printf("shapes2 \n");
for (int i = 0; i < num_spatial_axes_; ++i) {
bottom_shape_data[first_spatial_axis+i] = bottom[0]->shape(first_spatial_axis+i);
top_shape_data[first_spatial_axis+i] = bottom[1]->shape(first_spatial_axis+i);
}
// printf("line size \n");
line_size_ = top_shape_data[num_axes_-1];
// printf("done \n");
}
