Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Refactor and add naive prelu support #23

Merged
merged 4 commits into from
Jan 10, 2019
Merged

Refactor and add naive prelu support #23

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
df3cc77
Refactor and support prelu(not tested)
daquexian Jan 10, 2019
6e38bd3
Clear state on convert finishing
daquexian Jan 10, 2019
27f5b15
Fix prelu bug, add some operator, add res_shape in validate_onnx.py
daquexian Jan 10, 2019
7e930fa
Fuse two mul scalar in prelu
daquexian Jan 10, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions binaries/dnn_infer.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,8 +19,8 @@
using std::string; using std::cout; using std::endl;
using Clock = std::chrono::high_resolution_clock;

#define WARM_UP 5
#define RUNS 20
#define WARM_UP 0
#define RUNS 1

// ./dnn_save_result daqName outputBlob [input]
int main(int argc, char **argv) {
Expand Down
26 changes: 25 additions & 1 deletion common/daq.fbs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@ namespace DNN;
enum DataType:byte { Float32 = 0, Int8 }
enum FuseCode:byte { None = 0, Relu, Relu1, Relu6 }
enum LayerType:byte { Conv2D = 0, AvePool, MaxPool, Relu, Softmax, FC, Add, Concat,
DepthwiseConv2D, BatchToSpace, SpaceToBatch, StridedSlice }
DepthwiseConv2D, BatchToSpace, SpaceToBatch, StridedSlice, Mul, AddScalar, MulScalar }

table Tensor {
data_type:DataType;
Expand Down Expand Up @@ -112,6 +112,27 @@ table Concat {
output:string;
}

table Mul {
input1:string;
input2:string;
fuse:FuseCode;
output:string;
}

table AddScalar {
input1:string;
input2:float;
fuse:FuseCode;
output:string;
}

table MulScalar {
input1:string;
input2:float;
fuse:FuseCode;
output:string;
}

table Layer {
type:LayerType;
conv2d_param:Conv2D;
Expand All @@ -126,6 +147,9 @@ table Layer {
batch_to_space_param:BatchToSpace;
space_to_batch_param:SpaceToBatch;
strided_slice_param:StridedSlice;
mul_param:Mul;
add_scalar_param:AddScalar;
mul_scalar_param:MulScalar;
}

table Model {
Expand Down
Loading