Yolo_v3_structure

Yolo_v3_structure.py

def YOLOv3(input_layer, NUM_CLASS):
    # After the input layer enters the Darknet-53 network, we get three branches
    route_1, route_2, conv = darknet53(input_layer)
    # See the orange module (DBL) in the figure above, a total of 5 Subconvolution operation
    conv = convolutional(conv, (1, 1, 1024,  512))
    conv = convolutional(conv, (3, 3,  512, 1024))
    conv = convolutional(conv, (1, 1, 1024,  512))
    conv = convolutional(conv, (3, 3,  512, 1024))
    conv = convolutional(conv, (1, 1, 1024,  512))
    conv_lobj_branch = convolutional(conv, (3, 3, 512, 1024))

    # conv_lbbox is used to predict large-sized objects , Shape = [None, 13, 13, 255] 
    conv_lbbox = convolutional(conv_lobj_branch, (1, 1, 1024, 3*(NUM_CLASS + 5)), activate=False, bn=False)

    conv = convolutional(conv, (1, 1,  512,  256))
    # upsample here uses the nearest neighbor interpolation method, which has the advantage that the
    # upsampling process does not need to learn, thereby reducing the network parameter  
    conv = upsample(conv)

    conv = tf.concat([conv, route_2], axis=-1)
    conv = convolutional(conv, (1, 1, 768, 256))
    conv = convolutional(conv, (3, 3, 256, 512))
    conv = convolutional(conv, (1, 1, 512, 256))
    conv = convolutional(conv, (3, 3, 256, 512))
    conv = convolutional(conv, (1, 1, 512, 256))
    conv_mobj_branch = convolutional(conv, (3, 3, 256, 512))

    # conv_mbbox is used to predict medium-sized objects, shape = [None, 26, 26, 255]
    conv_mbbox = convolutional(conv_mobj_branch, (1, 1, 512, 3*(NUM_CLASS + 5)), activate=False, bn=False)

    conv = convolutional(conv, (1, 1, 256, 128))
    conv = upsample(conv)

    conv = tf.concat([conv, route_1], axis=-1)
    conv = convolutional(conv, (1, 1, 384, 128))
    conv = convolutional(conv, (3, 3, 128, 256))
    conv = convolutional(conv, (1, 1, 256, 128))
    conv = convolutional(conv, (3, 3, 128, 256))
    conv = convolutional(conv, (1, 1, 256, 128))
    conv_sobj_branch = convolutional(conv, (3, 3, 128, 256))

    # conv_sbbox is used to predict small size objects, shape = [None, 52, 52, 255]
    conv_sbbox = convolutional(conv_sobj_branch, (1, 1, 256, 3*(NUM_CLASS +5)), activate=False, bn=False)

    return [conv_sbbox, conv_mbbox, conv_lbbox]