marian-nmt/marian
1
1
Fork 0
mirror of https://github.com/marian-nmt/marian.git synced 2024-09-11 06:15:56 +03:00
Code Issues Packages Projects Releases Wiki Activity

Replaced softmax with fast softmax in MNIST.

Browse Source
This commit is contained in:
Andre Martins 2016-09-15 15:10:03 +01:00
parent 6d3f67e955
commit 61d8b3cb83
2 changed files with 76 additions and 70 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

144
src/test.cu
View File

@ -9,9 +9,10 @@ int main(int argc, char** argv) {
/*auto images = datasets::mnist::ReadImages("../examples/mnist/t10k-images-idx3-ubyte", numImg);*/
/*auto labels = datasets::mnist::ReadLabels("../examples/mnist/t10k-labels-idx1-ubyte", numImg);*/
#if 1
using namespace marian;
using namespace keywords;
Expr x = input(shape={1, 2});
Expr y = input(shape={1, 2});
@ -41,75 +42,80 @@ int main(int argc, char** argv) {
std::cerr << graph.val().Debug() << std::endl;
std::cerr << w.grad().Debug() << std::endl;
//std::cerr << b.grad().Debug() << std::endl;
#else
// using namespace marian;
// using namespace keywords;
//
// const size_t BATCH_SIZE = 500;
// const size_t IMAGE_SIZE = 784;
// const size_t LABEL_SIZE = 10;
//
// Expr x = input(shape={whatevs, IMAGE_SIZE}, name="X");
// Expr y = input(shape={whatevs, LABEL_SIZE}, name="Y");
//
// Expr w = param(shape={IMAGE_SIZE, LABEL_SIZE}, name="W0");
// Expr b = param(shape={1, LABEL_SIZE}, name="b0");
//
// Expr z = dot(x, w) + b;
// Expr lr = softmax(z, axis=1, name="pred");
// Expr graph = -mean(sum(y * log(lr), axis=1), axis=0, name="cost");
// //cerr << "x=" << Debug(lr.val().shape()) << endl;
//
// int numofdata;
// //vector<float> images = datasets::mnist::ReadImages("../examples/mnist/t10k-images-idx3-ubyte", numofdata, IMAGE_SIZE);
// //vector<float> labels = datasets::mnist::ReadLabels("../examples/mnist/t10k-labels-idx1-ubyte", numofdata, LABEL_SIZE);
// vector<float> images = datasets::mnist::ReadImages("../examples/mnist/train-images-idx3-ubyte", numofdata, IMAGE_SIZE);
// vector<float> labels = datasets::mnist::ReadLabels("../examples/mnist/train-labels-idx1-ubyte", numofdata, LABEL_SIZE);
// cerr << "images=" << images.size() << " labels=" << labels.size() << endl;
// cerr << "numofdata=" << numofdata << endl;
//
// size_t startInd = 0;
// size_t startIndData = 0;
// while (startInd < numofdata) {
// size_t batchSize = (startInd + BATCH_SIZE < numofdata) ? BATCH_SIZE : numofdata - startInd;
// cerr << "startInd=" << startInd
// << " startIndData=" << startIndData
// << " batchSize=" << batchSize << endl;
//
// Tensor tx({numofdata, IMAGE_SIZE}, 1);
// Tensor ty({numofdata, LABEL_SIZE}, 1);
//
// tx.Load(images.begin() + startIndData, images.begin() + startIndData + batchSize * IMAGE_SIZE);
// ty.Load(labels.begin() + startInd, labels.begin() + startInd + batchSize);
//
// //cerr << "tx=" << Debug(tx.shape()) << endl;
// //cerr << "ty=" << Debug(ty.shape()) << endl;
//
// x = tx;
// y = ty;
//
// cerr << "x=" << Debug(x.val().shape()) << endl;
// cerr << "y=" << Debug(y.val().shape()) << endl;
//
//
// graph.forward(batchSize);
//
// cerr << "w=" << Debug(w.val().shape()) << endl;
// cerr << "b=" << Debug(b.val().shape()) << endl;
// std::cerr << "z: " << Debug(z.val().shape()) << endl;
// std::cerr << "lr: " << Debug(lr.val().shape()) << endl;
// std::cerr << "Log-likelihood: " << Debug(graph.val().shape()) << endl ;
//
// //std::cerr << "scores=" << scores.val().Debug() << endl;
// //std::cerr << "lr=" << lr.val().Debug() << endl;
//
// //graph.backward();
//
// //std::cerr << graph["pred"].val()[0] << std::endl;
//
// startInd += batchSize;
// startIndData += batchSize * IMAGE_SIZE;
// }
using namespace marian;
using namespace keywords;
using namespace std;
const size_t BATCH_SIZE = 500;
const size_t IMAGE_SIZE = 784;
const size_t LABEL_SIZE = 10;
Expr x = input(shape={whatevs, IMAGE_SIZE}, name="X");
Expr y = input(shape={whatevs, LABEL_SIZE}, name="Y");
Expr w = param(shape={IMAGE_SIZE, LABEL_SIZE}, name="W0");
Expr b = param(shape={1, LABEL_SIZE}, name="b0");
Expr z = dot(x, w) + b;
Expr lr = softmax(z, axis=1, name="pred");
Expr graph = -mean(sum(y * log(lr), axis=1), axis=0, name="cost");
//cerr << "x=" << Debug(lr.val().shape()) << endl;
int numofdata;
//vector<float> images = datasets::mnist::ReadImages("../examples/mnist/t10k-images-idx3-ubyte", numofdata, IMAGE_SIZE);
//vector<float> labels = datasets::mnist::ReadLabels("../examples/mnist/t10k-labels-idx1-ubyte", numofdata, LABEL_SIZE);
vector<float> images = datasets::mnist::ReadImages("../examples/mnist/train-images-idx3-ubyte", numofdata, IMAGE_SIZE);
vector<float> labels = datasets::mnist::ReadLabels("../examples/mnist/train-labels-idx1-ubyte", numofdata, LABEL_SIZE);
cerr << "images=" << images.size() << " labels=" << labels.size() << endl;
cerr << "numofdata=" << numofdata << endl;
size_t startInd = 0;
size_t startIndData = 0;
while (startInd < numofdata) {
size_t batchSize = (startInd + BATCH_SIZE < numofdata) ? BATCH_SIZE : numofdata - startInd;
cerr << "startInd=" << startInd
<< " startIndData=" << startIndData
<< " batchSize=" << batchSize << endl;
Tensor tx({numofdata, IMAGE_SIZE}, 1);
Tensor ty({numofdata, LABEL_SIZE}, 1);
tx.set(images.begin() + startIndData, images.begin() + startIndData + batchSize * IMAGE_SIZE);
ty.set(labels.begin() + startInd, labels.begin() + startInd + batchSize);
//cerr << "tx=" << Debug(tx.shape()) << endl;
//cerr << "ty=" << Debug(ty.shape()) << endl;
x = tx;
y = ty;
cerr << "x=" << Debug(x.val().shape()) << endl;
cerr << "y=" << Debug(y.val().shape()) << endl;
graph.forward(batchSize);
cerr << "w=" << Debug(w.val().shape()) << endl;
cerr << "b=" << Debug(b.val().shape()) << endl;
std::cerr << "z: " << Debug(z.val().shape()) << endl;
std::cerr << "lr: " << Debug(lr.val().shape()) << endl;
std::cerr << "Log-likelihood: " << graph.val().Debug() << endl ;
//std::cerr << "scores=" << scores.val().Debug() << endl;
//std::cerr << "lr=" << lr.val().Debug() << endl;
graph.backward();
std::cerr << w.grad().Debug() << std::endl;
//std::cerr << graph["pred"].val()[0] << std::endl;
startInd += batchSize;
startIndData += batchSize * IMAGE_SIZE;
}
#endif
return 0;
}

2
src/validate_mnist.cu
View File

@ -39,7 +39,7 @@ int main(int argc, char** argv) {
auto b = param(shape={1, LABEL_SIZE},
init=from_vector(bData));
auto probs = softmax(dot(x, w) + b, axis=1);
auto probs = softmax_fast(dot(x, w) + b, axis=1);
auto cost = -mean(sum(y * log(probs), axis=1), axis=0);
std::cerr << "Done." << std::endl;