def forward_gpu(self, x):
self.rand = cuda.empty_like(x[0])
y = cuda.empty_like(x[0])
cuda.get_generator().fill_uniform(self.rand)
self.scale = 1. / (1 - self.dropout_ratio)
self.kernel = cuda.elementwise(
'''float* y, const float* x, const float* rand, float dropout_ratio,
float scale''',
'y[i] = rand[i] < dropout_ratio ? 0 : scale * x[i]', 'dropout')
self.kernel(y, x[0], self.rand, self.dropout_ratio, self.scale)
return y,
def forward_gpu(self, x):
self.rand = cuda.empty_like(x[0])
y = cuda.empty_like(x[0])
cuda.get_generator().fill_uniform(self.rand)
self.scale = 1. / (1 - self.dropout_ratio)
self.kernel = cuda.elementwise(
'''float* y, const float* x, const float* rand, float dropout_ratio,
float scale''',
'y[i] = rand[i] < dropout_ratio ? 0 : scale * x[i]',
'dropout')
self.kernel(y, x[0], self.rand, self.dropout_ratio, self.scale)
return y,
def forward_gpu(self, inputs):
mean, ln_var = inputs
if self.eps is None:
self.eps = cuda.empty(ln_var.shape, numpy.float32)
cuda.get_generator().fill_normal(self.eps)
noise = cuda.empty_like(ln_var)
cuda.elementwise(
'float* noise, const float* v, const float* e',
'noise[i] = __expf(v[i] * 0.5f) * e[i];',
'gaussian_forward'
)(noise, ln_var, self.eps)
self.noise = noise
return mean + self.noise,
def forward_gpu(self, inputs):
mean, ln_var = inputs
if self.eps is None:
self.eps = cuda.empty(ln_var.shape, numpy.float32)
cuda.get_generator().fill_normal(self.eps)
noise = cuda.empty_like(ln_var)
cuda.elementwise(
'float* noise, const float* v, const float* e',
'noise[i] = __expf(v[i] * 0.5f) * e[i];',
'gaussian_forward'
)(noise, ln_var, self.eps)
self.noise = noise
return mean + self.noise,
def sample_gpu(self, shape):
ps = cuda.empty(shape, numpy.float32)
cuda.get_generator().fill_uniform(ps)
vs = cuda.empty(shape, numpy.int32)
cuda.elementwise(
'''int* vs, const float* ps, const float* threshold,
const int* values, int b''', '''
float pb = ps[i] * b;
int index = __float2int_rd(pb);
// fill_uniform sometimes returns 1.0, so we need to check index
if (index >= b) {
index = 0;
}
int lr = threshold[index] < pb - index;
vs[i] = values[index * 2 + lr];
''', 'walker_alias_sample')(vs, ps, self.threshold, self.values,
len(self.threshold))
return vs
def sample_gpu(self, shape):
ps = cuda.empty(shape, numpy.float32)
cuda.get_generator().fill_uniform(ps)
vs = cuda.empty(shape, numpy.int32)
cuda.elementwise(
'''int* vs, const float* ps, const float* threshold,
const int* values, int b''',
'''
float pb = ps[i] * b;
int index = __float2int_rd(pb);
// fill_uniform sometimes returns 1.0, so we need to check index
if (index >= b) {
index = 0;
}
int lr = threshold[index] < pb - index;
vs[i] = values[index * 2 + lr];
''',
'walker_alias_sample'
)(vs, ps, self.threshold, self.values, len(self.threshold))
return vs
