def test_leaky_relu(self): """Test creation of a LeakyReLU activation""" activation_name = 'LeakyReLU' args = {} activation = activation_factory.create(activation_name, **args) self.assertEqual(activation._get_name(), activation_name)
def test_softmax(self): """Test creation of a Softmax activation""" activation_name = 'Softmax' args = {} activation = activation_factory.create(activation_name, **args) self.assertEqual(activation._get_name(), activation_name) x = torch.empty(10, 2) y = activation(x) assert_array_equal(y, torch.softmax(x, -1))
def test_sigmoid(self): """Test creation of a Sigmoid activation""" activation_name = 'Sigmoid' args = {} activation = activation_factory.create(activation_name, **args) self.assertEqual(activation._get_name(), activation_name) x = torch.empty(10) y = activation(x) assert_array_equal(y, torch.sigmoid(x))
def test_relu(self): """Test creation of a ReLU activation""" activation_name = 'ReLU' args = {} activation = activation_factory.create(activation_name, **args) self.assertEqual(activation._get_name(), activation_name) x = torch.ones(10) * -1 y = activation(x) self.assertEqual(len(torch.nonzero(y, as_tuple=False)), 0)
def __init__(self, block, layers, in_channels=3, zero_init_residual=False, groups=1, width_per_group=64, replace_stride_with_dilation=None, norm_layer=None, activation={'name': 'ReLU', 'params': {'inplace': True}}): super(ResNet, self).__init__() if norm_layer is None: norm_layer = nn.BatchNorm2d self._norm_layer = norm_layer self.inplanes = 64 self.dilation = 1 if replace_stride_with_dilation is None: # each element in the tuple indicates if we should replace # the 2x2 stride with a dilated convolution instead replace_stride_with_dilation = [False, False, False] if len(replace_stride_with_dilation) != 3: raise ValueError("replace_stride_with_dilation should be None " "or a 3-element tuple, got {}".format( replace_stride_with_dilation)) self.groups = groups self.base_width = width_per_group self.conv1 = nn.Conv2d(in_channels, self.inplanes, kernel_size=7, stride=2, padding=3, bias=False) self.bn1 = norm_layer(self.inplanes) self.activation = activation_factory.create( activation['name'], **activation['params']) self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1) self.layer1 = self._make_layer(block, 64, layers[0]) self.layer2 = self._make_layer(block, 128, layers[1], stride=2, dilate=replace_stride_with_dilation[0]) self.layer3 = self._make_layer(block, 256, layers[2], stride=2, dilate=replace_stride_with_dilation[1]) self.layer4 = self._make_layer(block, 512, layers[3], stride=2, dilate=replace_stride_with_dilation[2]) for m in self.modules(): if isinstance(m, nn.Conv2d): nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu') elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)): nn.init.constant_(m.weight, 1) nn.init.constant_(m.bias, 0) # Zero-initialize the last BN in each residual branch, # so that the residual branch starts with zeros, and each residual # block behaves like an identity. This improves the model by 0.2~0.3% # according to https://arxiv.org/abs/1706.02677 if zero_init_residual: for m in self.modules(): if isinstance(m, Bottleneck): nn.init.constant_(m.bn3.weight, 0) elif isinstance(m, BasicBlock): nn.init.constant_(m.bn2.weight, 0)