Yolo_v3_Bounding_Box

Yolo_v3_Bounding_Box.py

def decode(conv_output, NUM_CLASS, i=0):
    # where i = 0, 1 or 2 to correspond to the three grid scales  
    conv_shape       = tf.shape(conv_output)
    batch_size       = conv_shape[0]
    output_size      = conv_shape[1]

    conv_output = tf.reshape(conv_output, (batch_size, output_size, output_size, 3, 5 + NUM_CLASS))

    conv_raw_dxdy = conv_output[:, :, :, :, 0:2] # offset of center position     
    conv_raw_dwdh = conv_output[:, :, :, :, 2:4] # Prediction box length and width offset
    conv_raw_conf = conv_output[:, :, :, :, 4:5] # confidence of the prediction box
    conv_raw_prob = conv_output[:, :, :, :, 5: ] # category probability of the prediction box 

    # next need Draw the grid. Where output_size is equal to 13, 26 or 52  
    y = tf.range(output_size, dtype=tf.int32)
    y = tf.expand_dims(y, -1)
    y = tf.tile(y, [1, output_size])
    x = tf.range(output_size,dtype=tf.int32)
    x = tf.expand_dims(x, 0)
    x = tf.tile(x, [output_size, 1])

    xy_grid = tf.concat([x[:, :, tf.newaxis], y[:, :, tf.newaxis]], axis=-1)
    xy_grid = tf.tile(xy_grid[tf.newaxis, :, :, tf.newaxis, :], [batch_size, 1, 1, 3, 1])
    xy_grid = tf.cast(xy_grid, tf.float32)

    # Calculate the center position of the prediction box:
    pred_xy = (tf.sigmoid(conv_raw_dxdy) + xy_grid) * STRIDES[i]
    # Calculate the length and width of the prediction box:
    pred_wh = (tf.exp(conv_raw_dwdh) * ANCHORS[i]) * STRIDES[i]

    pred_xywh = tf.concat([pred_xy, pred_wh], axis=-1)
    pred_conf = tf.sigmoid(conv_raw_conf) # object box calculates the predicted confidence
    pred_prob = tf.sigmoid(conv_raw_prob) # calculating the predicted probability category box object

    # calculating the predicted probability category box object
    return tf.concat([pred_xywh, pred_conf, pred_prob], axis=-1)