YOLOv3 From Scratch Using PyTorch
class YOLOv3(nn.Module):
def __init__(self, in_channels=3, num_classes=20):
super().__init__()
self.num_classes = num_classes
self.in_channels = in_channels
self.layers = nn.ModuleList([
CNNBlock(in_channels, 32, kernel_size=3, stride=1, padding=1),
CNNBlock(32, 64, kernel_size=3, stride=2, padding=1),
ResidualBlock(64, num_repeats=1),
CNNBlock(64, 128, kernel_size=3, stride=2, padding=1),
ResidualBlock(128, num_repeats=2),
CNNBlock(128, 256, kernel_size=3, stride=2, padding=1),
ResidualBlock(256, num_repeats=8),
CNNBlock(256, 512, kernel_size=3, stride=2, padding=1),
ResidualBlock(512, num_repeats=8),
CNNBlock(512, 1024, kernel_size=3, stride=2, padding=1),
ResidualBlock(1024, num_repeats=4),
CNNBlock(1024, 512, kernel_size=1, stride=1, padding=0),
CNNBlock(512, 1024, kernel_size=3, stride=1, padding=1),
ResidualBlock(1024, use_residual=False, num_repeats=1),
CNNBlock(1024, 512, kernel_size=1, stride=1, padding=0),
ScalePrediction(512, num_classes=num_classes),
CNNBlock(512, 256, kernel_size=1, stride=1, padding=0),
nn.Upsample(scale_factor=2),
CNNBlock(768, 256, kernel_size=1, stride=1, padding=0),
CNNBlock(256, 512, kernel_size=3, stride=1, padding=1),
ResidualBlock(512, use_residual=False, num_repeats=1),
CNNBlock(512, 256, kernel_size=1, stride=1, padding=0),
ScalePrediction(256, num_classes=num_classes),
CNNBlock(256, 128, kernel_size=1, stride=1, padding=0),
nn.Upsample(scale_factor=2),
CNNBlock(384, 128, kernel_size=1, stride=1, padding=0),
CNNBlock(128, 256, kernel_size=3, stride=1, padding=1),
ResidualBlock(256, use_residual=False, num_repeats=1),
CNNBlock(256, 128, kernel_size=1, stride=1, padding=0),
ScalePrediction(128, num_classes=num_classes)
])
def forward(self, x):
outputs = []
route_connections = []
for layer in self.layers:
if isinstance(layer, ScalePrediction):
outputs.append(layer(x))
continue
x = layer(x)
if isinstance(layer, ResidualBlock) and layer.num_repeats == 8:
route_connections.append(x)
elif isinstance(layer, nn.Upsample):
x = torch.cat([x, route_connections[-1]], dim=1)
route_connections.pop()
return outputs
class YOLOv3(nn.Module):
def __init__(self, in_channels=3, num_classes=20):
super().__init__()
self.num_classes = num_classes
self.in_channels = in_channels
self.layers = nn.ModuleList([
CNNBlock(in_channels, 32, kernel_size=3, stride=1, padding=1),
CNNBlock(32, 64, kernel_size=3, stride=2, padding=1),
ResidualBlock(64, num_repeats=1),
CNNBlock(64, 128, kernel_size=3, stride=2, padding=1),
ResidualBlock(128, num_repeats=2),
CNNBlock(128, 256, kernel_size=3, stride=2, padding=1),
ResidualBlock(256, num_repeats=8),
CNNBlock(256, 512, kernel_size=3, stride=2, padding=1),
ResidualBlock(512, num_repeats=8),
CNNBlock(512, 1024, kernel_size=3, stride=2, padding=1),
ResidualBlock(1024, num_repeats=4),
CNNBlock(1024, 512, kernel_size=1, stride=1, padding=0),
CNNBlock(512, 1024, kernel_size=3, stride=1, padding=1),
ResidualBlock(1024, use_residual=False, num_repeats=1),
CNNBlock(1024, 512, kernel_size=1, stride=1, padding=0),
ScalePrediction(512, num_classes=num_classes),
CNNBlock(512, 256, kernel_size=1, stride=1, padding=0),
nn.Upsample(scale_factor=2),
CNNBlock(768, 256, kernel_size=1, stride=1, padding=0),
CNNBlock(256, 512, kernel_size=3, stride=1, padding=1),
ResidualBlock(512, use_residual=False, num_repeats=1),
CNNBlock(512, 256, kernel_size=1, stride=1, padding=0),
ScalePrediction(256, num_classes=num_classes),
CNNBlock(256, 128, kernel_size=1, stride=1, padding=0),
nn.Upsample(scale_factor=2),
CNNBlock(384, 128, kernel_size=1, stride=1, padding=0),
CNNBlock(128, 256, kernel_size=3, stride=1, padding=1),
ResidualBlock(256, use_residual=False, num_repeats=1),
CNNBlock(256, 128, kernel_size=1, stride=1, padding=0),
ScalePrediction(128, num_classes=num_classes)
])
def forward(self, x):
outputs = []
route_connections = []
for layer in self.layers:
if isinstance(layer, ScalePrediction):
outputs.append(layer(x))
continue
x = layer(x)
if isinstance(layer, ResidualBlock) and layer.num_repeats == 8:
route_connections.append(x)
elif isinstance(layer, nn.Upsample):
x = torch.cat([x, route_connections[-1]], dim=1)
route_connections.pop()
return outputs
Denial of responsibility! Techno Blender is an automatic aggregator of the all world’s media. In each content, the hyperlink to the primary source is specified. All trademarks belong to their rightful owners, all materials to their authors. If you are the owner of the content and do not want us to publish your materials, please contact us by email – [email protected]. The content will be deleted within 24 hours.