Skip to content

D
dlib
Commit af76e826 authored by Dennis Francis's avatar Dennis Francis
Browse files
Options

converted tabs to spaces in the indentation

parent cd4b62b4
Hide whitespace changes
Inline Side-by-side
Showing with 92 additions and 92 deletions
dlib/dnn/loss.h
View file @ af76e826
...@@ -1305,70 +1305,70 @@ namespace dlib ...@@ -1305,70 +1305,70 @@ namespace dlib
typename SUB_TYPE, typename SUB_TYPE,
typename label_iterator typename label_iterator
> >
void to_label ( void to_label (
const tensor& input_tensor, const tensor& input_tensor,
const SUB_TYPE& sub, const SUB_TYPE& sub,
label_iterator iter label_iterator iter
) const ) const
{ {
DLIB_CASSERT(sub.sample_expansion_factor() == 1); DLIB_CASSERT(sub.sample_expansion_factor() == 1);
const tensor& output_tensor = sub.get_output(); const tensor& output_tensor = sub.get_output();
DLIB_CASSERT(output_tensor.nr() == 1 && DLIB_CASSERT(output_tensor.nr() == 1 &&
output_tensor.nc() == 1 && output_tensor.nc() == 1 &&
output_tensor.k() == 1); output_tensor.k() == 1);
DLIB_CASSERT(input_tensor.num_samples() == output_tensor.num_samples()); DLIB_CASSERT(input_tensor.num_samples() == output_tensor.num_samples());
const float* out_data = output_tensor.host(); const float* out_data = output_tensor.host();
for (long i = 0; i < output_tensor.num_samples(); ++i) for (long i = 0; i < output_tensor.num_samples(); ++i)
{ {
*iter++ = out_data[i]; *iter++ = out_data[i];
}
} }
}
template < template <
typename const_label_iterator, typename const_label_iterator,
typename SUBNET typename SUBNET
> >
double compute_loss_value_and_gradient ( double compute_loss_value_and_gradient (
const tensor& input_tensor, const tensor& input_tensor,
const_label_iterator truth, const_label_iterator truth,
SUBNET& sub SUBNET& sub
) const ) const
{
const tensor& output_tensor = sub.get_output();
tensor& grad = sub.get_gradient_input();
DLIB_CASSERT(sub.sample_expansion_factor() == 1);
DLIB_CASSERT(input_tensor.num_samples() != 0);
DLIB_CASSERT(input_tensor.num_samples()%sub.sample_expansion_factor() == 0);
DLIB_CASSERT(input_tensor.num_samples() == grad.num_samples());
DLIB_CASSERT(input_tensor.num_samples() == output_tensor.num_samples());
DLIB_CASSERT(output_tensor.nr() == 1 &&
output_tensor.nc() == 1 &&
output_tensor.k() == 1);
DLIB_CASSERT(grad.nr() == 1 &&
grad.nc() == 1 &&
grad.k() == 1);
// The loss we output is the average loss over the mini-batch.
const double scale = 1.0/output_tensor.num_samples();
double loss = 0;
float* g = grad.host_write_only();
const float* out_data = output_tensor.host();
for (long i = 0; i < output_tensor.num_samples(); ++i)
{ {
const float y = *truth++; const tensor& output_tensor = sub.get_output();
const float temp1 = y - out_data[i]; tensor& grad = sub.get_gradient_input();
const float temp2 = scale*temp1;
loss += 0.5*temp2*temp1; DLIB_CASSERT(sub.sample_expansion_factor() == 1);
g[i] = -temp2; DLIB_CASSERT(input_tensor.num_samples() != 0);
DLIB_CASSERT(input_tensor.num_samples()%sub.sample_expansion_factor() == 0);
DLIB_CASSERT(input_tensor.num_samples() == grad.num_samples());
DLIB_CASSERT(input_tensor.num_samples() == output_tensor.num_samples());
DLIB_CASSERT(output_tensor.nr() == 1 &&
output_tensor.nc() == 1 &&
output_tensor.k() == 1);
DLIB_CASSERT(grad.nr() == 1 &&
grad.nc() == 1 &&
grad.k() == 1);
// The loss we output is the average loss over the mini-batch.
const double scale = 1.0/output_tensor.num_samples();
double loss = 0;
float* g = grad.host_write_only();
const float* out_data = output_tensor.host();
for (long i = 0; i < output_tensor.num_samples(); ++i)
{
const float y = *truth++;
const float temp1 = y - out_data[i];
const float temp2 = scale*temp1;
loss += 0.5*temp2*temp1;
g[i] = -temp2;
}
return loss;
} }
return loss;
}
friend void serialize(const loss_mean_squared_& , std::ostream& out) friend void serialize(const loss_mean_squared_& , std::ostream& out)
{ {
...@@ -1397,7 +1397,7 @@ namespace dlib ...@@ -1397,7 +1397,7 @@ namespace dlib
}; };
template <typename SUBNET> template <typename SUBNET>
using loss_mean_squared = add_loss_layer<loss_mean_squared_, SUBNET>; using loss_mean_squared = add_loss_layer<loss_mean_squared_, SUBNET>;
// ---------------------------------------------------------------------------------------- // ----------------------------------------------------------------------------------------
......
dlib/test/dnn.cpp
View file @ af76e826
...@@ -1743,45 +1743,45 @@ namespace ...@@ -1743,45 +1743,45 @@ namespace
void test_simple_linear_regression() void test_simple_linear_regression()
{ {
::std::vector<matrix<double>> x(100); ::std::vector<matrix<double>> x(100);
::std::vector<float> y(100); ::std::vector<float> y(100);
::std::default_random_engine generator(16); ::std::default_random_engine generator(16);
::std::normal_distribution<float> distribution(0,5); ::std::normal_distribution<float> distribution(0,5);
const float true_intercept = 50.0; const float true_intercept = 50.0;
const float true_slope = 10.0; const float true_slope = 10.0;
for ( int ii = 0; ii < 100; ++ii ) for ( int ii = 0; ii < 100; ++ii )
{ {
const double val = static_cast<double>(ii); const double val = static_cast<double>(ii);
matrix<double> tmp(1,1); matrix<double> tmp(1,1);
tmp = val; tmp = val;
x[ii] = tmp; x[ii] = tmp;
y[ii] = (true_intercept + true_slope*static_cast<float>(val) + distribution(generator)); y[ii] = (true_intercept + true_slope*static_cast<float>(val) + distribution(generator));
} }
using net_type = loss_mean_squared< using net_type = loss_mean_squared<
fc< fc<
1, input<matrix<double>> 1, input<matrix<double>>
> >
>; >;
net_type net; net_type net;
layer<1>(net).layer_details().set_bias_learning_rate_multiplier(300); layer<1>(net).layer_details().set_bias_learning_rate_multiplier(300);
sgd defsolver; sgd defsolver;
dnn_trainer<net_type> trainer(net, defsolver); dnn_trainer<net_type> trainer(net, defsolver);
trainer.set_learning_rate(0.00001); trainer.set_learning_rate(0.00001);
trainer.set_mini_batch_size(50); trainer.set_mini_batch_size(50);
trainer.set_max_num_epochs(170); trainer.set_max_num_epochs(170);
trainer.train(x, y); trainer.train(x, y);
const float slope = layer<1>(net).layer_details().get_weights().host()[0]; const float slope = layer<1>(net).layer_details().get_weights().host()[0];
const float slope_error = abs(true_slope - slope); const float slope_error = abs(true_slope - slope);
const float intercept = layer<1>(net).layer_details().get_biases().host()[0]; const float intercept = layer<1>(net).layer_details().get_biases().host()[0];
const float intercept_error = abs(true_intercept - intercept); const float intercept_error = abs(true_intercept - intercept);
const float eps_slope = 0.5, eps_intercept = 1.0; const float eps_slope = 0.5, eps_intercept = 1.0;
DLIB_TEST_MSG(slope_error <= eps_slope, DLIB_TEST_MSG(slope_error <= eps_slope,
"Expected slope = " << true_slope << " Estimated slope = " << slope << " Error limit = " << eps_slope); "Expected slope = " << true_slope << " Estimated slope = " << slope << " Error limit = " << eps_slope);
DLIB_TEST_MSG(intercept_error <= eps_intercept, DLIB_TEST_MSG(intercept_error <= eps_intercept,
"Expected intercept = " << true_intercept << " Estimated intercept = " << intercept << " Error limit = " << eps_intercept); "Expected intercept = " << true_intercept << " Estimated intercept = " << intercept << " Error limit = " << eps_intercept);
} }
...@@ -1852,7 +1852,7 @@ namespace ...@@ -1852,7 +1852,7 @@ namespace
test_visit_funcions(); test_visit_funcions();
test_copy_tensor_cpu(); test_copy_tensor_cpu();
test_concat(); test_concat();
test_simple_linear_regression(); test_simple_linear_regression();
} }
void perform_test() void perform_test()
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment