5. convolution and upsample

if (block["type"] == "convolutional"):
         activation = block["activation"]
         filters = int(block["filters"])
         kernel_size = int(block["size"])
         strides = int(block["stride"])
         use_bias= False if ("batch_normalize" in block) else True
         pad = (kernel_size - 1) // 2
         conv = nn.Conv2d(in_channels=channels, out_channels=filters, kernel_size=kernel_size, 
                             stride=strides, padding=pad, bias = use_bias)
            
         seq.add_module("conv_{0}".format(i), conv)
            
         if "batch_normalize" in block:
                bn = nn.BatchNorm2d(filters)
                seq.add_module("batch_norm_{0}".format(i), bn)

         if activation == "leaky":
                activn = nn.LeakyReLU(0.1, inplace = True)
                seq.add_module("leaky_{0}".format(i), activn)
            
elif (block["type"] == "upsample"):
            upsample = nn.Upsample(scale_factor = 2, mode = "bilinear")
            seq.add_module("upsample_{}".format(i), upsample)