upsample层
#If it's an upsampling layer
#We use Bilinear2dUpsampling
elif (x["type"] == "upsample"):
stride = int(x["stride"])
upsample = nn.Upsample(scale_factor = 2, mode = "bilinear")
module.add_module("upsample_{}".format(index), upsample)
route层
[route]
layers = -4
[route]
layers = -1, 61
首先是解析配置文件,然后将相应层的feature map 连接起来作为输出
#If it is a route layer
elif (x["type"] == "route"):
x["layers"] = x["layers"].split(',')
#Start of a route
start = int(x["layers"][0])
#end, if there exists one.
try:
end = int(x["layers"][1])
except:
end = 0
#Positive anotation
if start > 0:
start = start - index #start转换成相对于当前layer的偏移
if end > 0:
end = end - index
#end转换成相对于当前layer的偏移
route = EmptyLayer()
module.add_module("route_{0}".format(index), route)
if end < 0: #route层concat当前layer前面的某2个layer,所以index>0是无意义的.
filters = output_filters[index + start] + output_filters[index + end]
else:
filters= output_filters[index + start]
这里我们自定义了一个EmptyLayer
class EmptyLayer(nn.Module):
def __init__(self):
super(EmptyLayer, self).__init__()
这里定义EmptyLayer是为了代码的简便起见.在pytorch里定义一个自定义的layer.要写一个类,继承自nn.Module,然后实现forward方法.
关于如何定义一个自定义layer,参见下面的link.
https://pytorch.org/tutorials/beginner/examples_nn/two_layer_net_module.html
import torch
class TwoLayerNet(torch.nn.Module):
def __init__(self, D_in, H, D_out):
"""
In the constructor we instantiate two nn.Linear modules and assign them as
member variables.
"""
super(TwoLayerNet, self).__init__()
self.linear1 = torch.nn.Linear(D_in, H)
self.linear2 = torch.nn.Linear(H, D_out)
def forward(self, x):
"""
In the forward function we accept a Tensor of input data and we must return
a Tensor of output data. We can use Modules defined in the constructor as
well as arbitrary operators on Tensors.
"""
h_relu = self.linear1(x).clamp(min=0)
y_pred = self.linear2(h_relu)
return y_pred
# N is batch size; D_in is input dimension;
# H is hidden dimension; D_out is output dimension.
N, D_in, H, D_out = 64, 1000, 100, 10
# Create random Tensors to hold inputs and outputs
x = torch.randn(N, D_in)
y = torch.randn(N, D_out)
# Construct our model by instantiating the class defined above
model = TwoLayerNet(D_in, H, D_out)
# Construct our loss function and an Optimizer. The call to model.parameters()
# in the SGD constructor will contain the learnable parameters of the two
# nn.Linear modules which are members of the model.
criterion = torch.nn.MSELoss(reduction='sum')
optimizer = torch.optim.SGD(model.parameters(), lr=1e-4)
for t in range(500):
# Forward pass: Compute predicted y by passing x to the model
y_pred = model(x)
# Compute and print loss
loss = criterion(y_pred, y)
print(t, loss.item())
# Zero gradients, perform a backward pass, and update the weights.
optimizer.zero_grad()
loss.backward()
optimizer.step()
这里由于我们的route layer要做的事情很简单,就是concat两个layer里的feature map,调用torch.cat一行代码的事情,所以没必要定义一个RouteLayer了,直接在代表darknet的nn.Module的forward方法里做concat操作就可以啦.
shorcut层
#shortcut corresponds to skip connection
elif x["type"] == "shortcut":
shortcut = EmptyLayer()
module.add_module("shortcut_{}".format(index), shortcut)
和route层类似,这边也用个EmptyLayer替代.shortcut所做操作即对两个feature map做addition.
yolo层
yolo层负责根据feature map做预测
首先是解析出有效的anchors.然后用我们自己定义的layer保存这些anchors.然后生成一个module.
涉及到一个python语法super
详细地看: 简单地说就是为了安全地继承.记住怎么用的就行了.没必要深究
#Yolo is the detection layer
elif x["type"] == "yolo":
mask = x["mask"].split(",")
mask = [int(x) for x in mask]
anchors = x["anchors"].split(",")
anchors = [int(a) for a in anchors]
anchors = [(anchors[i], anchors[i+1]) for i in range(0, len(anchors),2)]
anchors = [anchors[i] for i in mask]
detection = DetectionLayer(anchors)
module.add_module("Detection_{}".format(index), detection)
#我们自己定义了一个yolo层
class DetectionLayer(nn.Module):
def __init__(self, anchors):
super(DetectionLayer, self).__init__()
self.anchors = anchors
测试代码
blocks = parse_cfg("cfg/yolov3.cfg")
print(create_modules(blocks))
输出如下
![image.png]()
