arunm8489

class DummyLayer(nn.Module):
    def __init__(self):
        super(DummyLayer, self).__init__()
        

        
class DetectionLayer(nn.Module):
    def __init__(self, anchors):
        super(DetectionLayer, self).__init__()
        self.anchors = anchors

arunm8489

blocks =  parse_cfg(cfgfile)
details,modules = model_initialization(blocks)
modules

arunm8489

class Darknet(nn.Module):
    def __init__(self, cfgfile):
        super(Darknet, self).__init__()
        self.blocks = parse_cfg(cfgfile)
        self.net_info, self.module_list = model_initialization(self.blocks)

arunm8489

def forward(self, x, CUDA=False):
    modules = self.blocks[1:]
    #We cache the outputs for the route layer
    outputs = {}   
    write = 0     
    for i, module in enumerate(modules):        
         module_type = (module["type"])

arunm8489

if module_type == "convolutional" or module_type == "upsample":
   x = self.module_list[i](x)
   outputs[i] = x

elif module_type == "route":
   layers = module["layers"]
   layers = [int(a) for a in layers]
   if len(layers) == 1:
      x = outputs[layers[0]]
   if len(layers) > 1:

arunm8489

elif module_type == 'yolo':
    anchors = self.module_list[i][0].anchors
                
    #Get the input dimensions
    inp_dim = int(self.net_info["height"])
    #Get the number of classes
    num_classes = int(module["classes"])
            
    #Transform 
    x = x.data   # get the data at that point

arunm8489

def detection_preprocess(x,inp_dim,anchors,num_classes,CUDA=False):
        """
        This function will take input_dimension_of_image,anchors and number of classes as input 
        """
        # x --> 4D feature map
        batch_size = x.size(0)
        grid_size = x.size(2)
        stride =  inp_dim // x.size(2)   # factor by which current feature map reduced from input
        #grid_size = inp_dim // stride
    

arunm8489

# x --> 4D feature map
batch_size = x.size(0)
grid_size = x.size(2)
# factor by which current feature map reduced from input
stride =  inp_dim // x.size(2)   
        
bbox_attrs = 5 + num_classes #5 + 80
num_anchors = len(anchors) #3
    
#eg detection input dimension [1, 255, 13, 13]

arunm8489

#eg detection input dimension [1, 255, 13, 13]
prediction = x.view(batch_size, bbox_attrs*num_anchors, grid_size*grid_size) # 1x255x169     
prediction = prediction.transpose(1,2).contiguous() #1x169x255
prediction = prediction.view(batch_size, grid_size*grid_size*num_anchors, bbox_attrs) #1x507x85

arunm8489

# the dimension of anchors is wrt original image.We will make it corresponding to feature map
anchors = [(a[0]/stride, a[1]/stride) for a in anchors]

#Sigmoid the  centre_X, centre_Y. and object confidencce
prediction[:,:,0] = torch.sigmoid(prediction[:,:,0])
prediction[:,:,1] = torch.sigmoid(prediction[:,:,1])
prediction[:,:,4] = torch.sigmoid(prediction[:,:,4])