影像辨識實作(二):Kaggle平台實作yolo映像辨識

2023 iThome 鐵人賽

DAY 27

自我挑戰組

AI研究系列第 27 篇

15th鐵人賽

熊晨佑

2023-10-07 22:23:38

483 瀏覽

分享至

匯入模組
import tensorflow as tf
import numpy as np
from PIL import Image, ImageDraw, ImageFont
from IPython.display import display
from seaborn import color_palette
import cv2

模型參數設置
_BATCH_NORM_DECAY = 0.9
_BATCH_NORM_EPSILON = 1e-05
_LEAKY_RELU = 0.1
_ANCHORS = [(10, 13), (16, 30), (33, 23),
(30, 61), (62, 45), (59, 119),
(116, 90), (156, 198), (373, 326)]
_MODEL_SIZE = (416, 416)

• BATCH_NORM_DECAY：提高CNN網路性能的正規化方法
• BATCH_NORM_EPSILON：穩定正規化過程
• LEAKY_RELU：激活函數
• ANCHORS：錨點，YOLO 通過調整錨點框的大小和位置來預測邊界框。
• MODEL_SIZE: YOLO 模型的輸入大小，即向素大小

模型設置

def batch_norm(inputs, training, data_format):
return tf.layers.batch_normalization(
inputs=inputs, axis=1 if data_format == 'channels_first' else 3,
momentum=_BATCH_NORM_DECAY, epsilon=_BATCH_NORM_EPSILON,
scale=True, training=training)

def fixed_padding(inputs, kernel_size, data_format):
pad_total = kernel_size - 1
pad_beg = pad_total // 2
pad_end = pad_total - pad_beg
if data_format == 'channels_first':
padded_inputs = tf.pad(inputs, [[0, 0], [0, 0],
[pad_beg, pad_end],
[pad_beg, pad_end]])
else:
padded_inputs = tf.pad(inputs, [[0, 0], [pad_beg, pad_end],
[pad_beg, pad_end], [0, 0]])
return padded_inputs

def conv2d_fixed_padding(inputs, filters, kernel_size, data_format, strides=1):
if strides > 1:
inputs = fixed_padding(inputs, kernel_size, data_format)
return tf.layers.conv2d(
inputs=inputs, filters=filters, kernel_size=kernel_size,
strides=strides, padding=('SAME' if strides == 1 else 'VALID'),
use_bias=False, data_format=data_format)

def darknet53_residual_block(inputs, filters, training, data_format, strides=1):
shortcut = inputs
inputs = conv2d_fixed_padding(
inputs, filters=filters, kernel_size=1, strides=strides,
data_format=data_format)
inputs = batch_norm(inputs, training=training, data_format=data_format)
inputs = tf.nn.leaky_relu(inputs, alpha=_LEAKY_RELU)
inputs = conv2d_fixed_padding(
inputs, filters=2 * filters, kernel_size=3, strides=strides,
data_format=data_format)
inputs = batch_norm(inputs, training=training, data_format=data_format)
inputs = tf.nn.leaky_relu(inputs, alpha=_LEAKY_RELU)
inputs += shortcut
return inputs

def darknet53(inputs, training, data_format):
inputs = conv2d_fixed_padding(inputs, filters=32, kernel_size=3,
data_format=data_format)
inputs = batch_norm(inputs, training=training, data_format=data_format)
inputs = tf.nn.leaky_relu(inputs, alpha=_LEAKY_RELU)
inputs = conv2d_fixed_padding(inputs, filters=64, kernel_size=3,
strides=2, data_format=data_format)
inputs = batch_norm(inputs, training=training, data_format=data_format)
inputs = tf.nn.leaky_relu(inputs, alpha=_LEAKY_RELU)
inputs = darknet53_residual_block(inputs, filters=32, training=training,
data_format=data_format)
inputs = conv2d_fixed_padding(inputs, filters=128, kernel_size=3,
strides=2, data_format=data_format)
inputs = batch_norm(inputs, training=training, data_format=data_format)
inputs = tf.nn.leaky_relu(inputs, alpha=_LEAKY_RELU)
for _ in range(2):
inputs = darknet53_residual_block(inputs, filters=64,
training=training,
data_format=data_format)
inputs = conv2d_fixed_padding(inputs, filters=256, kernel_size=3,
strides=2, data_format=data_format)
inputs = batch_norm(inputs, training=training, data_format=data_format)
inputs = tf.nn.leaky_relu(inputs, alpha=_LEAKY_RELU)
for _ in range(8):
inputs = darknet53_residual_block(inputs, filters=128,
training=training,
data_format=data_format)
route1 = inputs
inputs = conv2d_fixed_padding(inputs, filters=512, kernel_size=3,
strides=2, data_format=data_format)
inputs = batch_norm(inputs, training=training, data_format=data_format)
inputs = tf.nn.leaky_relu(inputs, alpha=_LEAKY_RELU)
for _ in range(8):
inputs = darknet53_residual_block(inputs, filters=256,
training=training,
data_format=data_format)
route2 = inputs
inputs = conv2d_fixed_padding(inputs, filters=1024, kernel_size=3,
strides=2, data_format=data_format)
inputs = batch_norm(inputs, training=training, data_format=data_format)
inputs = tf.nn.leaky_relu(inputs, alpha=_LEAKY_RELU)
for _ in range(4):
inputs = darknet53_residual_block(inputs, filters=512,
training=training,
data_format=data_format)
return route1, route2, inputs

def yolo_convolution_block(inputs, filters, training, data_format):
inputs = conv2d_fixed_padding(inputs, filters=filters, kernel_size=1,
data_format=data_format)
inputs = batch_norm(inputs, training=training, data_format=data_format)
inputs = tf.nn.leaky_relu(inputs, alpha=_LEAKY_RELU)
inputs = conv2d_fixed_padding(inputs, filters=2 * filters, kernel_size=3,
data_format=data_format)
inputs = batch_norm(inputs, training=training, data_format=data_format)
inputs = tf.nn.leaky_relu(inputs, alpha=_LEAKY_RELU)
inputs = conv2d_fixed_padding(inputs, filters=filters, kernel_size=1,
data_format=data_format)
inputs = batch_norm(inputs, training=training, data_format=data_format)
inputs = tf.nn.leaky_relu(inputs, alpha=_LEAKY_RELU)
inputs = conv2d_fixed_padding(inputs, filters=2 * filters, kernel_size=3,
data_format=data_format)
inputs = batch_norm(inputs, training=training, data_format=data_format)
inputs = tf.nn.leaky_relu(inputs, alpha=_LEAKY_RELU)
inputs = conv2d_fixed_padding(inputs, filters=filters, kernel_size=1,
data_format=data_format)
inputs = batch_norm(inputs, training=training, data_format=data_format)
inputs = tf.nn.leaky_relu(inputs, alpha=_LEAKY_RELU)
route = inputs
inputs = conv2d_fixed_padding(inputs, filters=2 * filters, kernel_size=3,
data_format=data_format)
inputs = batch_norm(inputs, training=training, data_format=data_format)
inputs = tf.nn.leaky_relu(inputs, alpha=_LEAKY_RELU)
return route, inputs

def yolo_layer(inputs, n_classes, anchors, img_size, data_format):
n_anchors = len(anchors)
inputs = tf.layers.conv2d(inputs, n_anchors * (5 + n_classes), 1, 1, use_bias=True, data_format=data_format)
shape = inputs.get_shape().as_list()
grid_shape = shape[2:4] if data_format == 'channels_first' else shape[1:3]
if data_format == 'channels_first':
inputs = tf.transpose(inputs, [0, 2, 3, 1])
inputs = tf.reshape(inputs, [-1, n_anchors * grid_shape[0] * grid_shape[1], 5 + n_classes])
strides = (img_size[0] // grid_shape[0], img_size[1] // grid_shape[1])
box_centers, box_shapes, confidence, classes = tf.split(inputs, [2, 2, 1, n_classes], axis=-1)
x = tf.range(grid_shape[0], dtype=tf.float32)
y = tf.range(grid_shape[1], dtype=tf.float32)
x_offset, y_offset = tf.meshgrid(x, y)
x_offset, y_offset = tf.reshape(x_offset, (-1, 1)), tf.reshape(y_offset, (-1, 1))
x_y_offset = tf.concat([x_offset, y_offset], axis=-1)
x_y_offset = tf.tile(x_y_offset, [1, n_anchors])
x_y_offset = tf.reshape(x_y_offset, [1, -1, 2])
box_centers = tf.nn.sigmoid(box_centers)
box_centers = (box_centers + x_y_offset) * strides
anchors = tf.tile(anchors, [grid_shape[0] * grid_shape[1], 1])
box_shapes = tf.exp(box_shapes) * tf.to_float(anchors)
confidence = tf.nn.sigmoid(confidence)
classes = tf.nn.sigmoid(classes)
inputs = tf.concat([box_centers, box_shapes, confidence, classes], axis=-1)
return inputs

def upsample(inputs, out_shape, data_format):
if data_format == 'channels_first':
inputs = tf.transpose(inputs, [0, 2, 3, 1])
new_height, new_width = out_shape[3], out_shape[2]
else:
new_height, new_width = out_shape[2], out_shape[1]
inputs = tf.image.resize_nearest_neighbor(inputs, (new_height, new_width))
if data_format == 'channels_first':
inputs = tf.transpose(inputs, [0, 3, 1, 2])
return inputs

def build_boxes(inputs):
center_x, center_y, width, height, confidence, classes = tf.split(inputs, [1, 1, 1, 1, 1, -1], axis=-1)
top_left_x, top_left_y = center_x - width / 2, center_y - height / 2
bottom_right_x, bottom_right_y = center_x + width / 2, center_y + height / 2
boxes = tf.concat([top_left_x, top_left_y, bottom_right_x, bottom_right_y, confidence, classes], axis=-1)
return boxes

def non_max_suppression(inputs, n_classes, max_output_size, iou_threshold, confidence_threshold):
batch = tf.unstack(inputs)
boxes_dicts = []
for boxes in batch:
boxes = tf.boolean_mask(boxes, boxes[:, 4] > confidence_threshold)
classes = tf.argmax(boxes[:, 5:], axis=-1)
classes = tf.expand_dims(tf.to_float(classes), axis=-1)
boxes = tf.concat([boxes[:, :5], classes], axis=-1)
boxes_dict = dict()
for cls in range(n_classes):
mask = tf.equal(boxes[:, 5], cls)
mask_shape = mask.get_shape()
if mask_shape.ndims != 0:
class_boxes = tf.boolean_mask(boxes, mask)
boxes_coords, boxes_conf_scores, _ = tf.split(class_boxes, [4, 1, -1], axis=-1)
boxes_conf_scores = tf.reshape(boxes_conf_scores, [-1])
indices = tf.image.non_max_suppression(boxes_coords, boxes_conf_scores, max_output_size, iou_threshold)
class_boxes = tf.gather(class_boxes, indices)
boxes_dict[cls] = class_boxes[:, :5]
boxes_dicts.append(boxes_dict)
return boxes_dicts

class Yolo_v3:
def init(self, n_classes, model_size, max_output_size, iou_threshold, confidence_threshold, data_format=None):
if not data_format:
data_format = 'channels_first' if tf.test.is_built_with_cuda() else 'channels_last'
self.n_classes, self.model_size, self.max_output_size, self.iou_threshold, self.confidence_threshold, self.data_format = n_classes, model_size, max_output_size, iou_threshold, confidence_threshold, data_format

def __call__(self, inputs, training):
    with tf.variable_scope('yolo_v3_model'):
        if self.data_format == 'channels_first':
            inputs = tf.transpose(inputs, [0, 3, 1, 2])
        inputs = inputs / 255
        route1, route2, inputs = darknet53(inputs, training=training, data_format=self.data_format)
        route, inputs = yolo_convolution_block(inputs, filters=512, training=training, data_format=self.data_format)
        detect1 = yolo_layer(inputs, n_classes=self.n_classes, anchors=_ANCHORS[6:9], img_size=self.model_size, data_format=self.data_format)
        inputs = conv2d_fixed_padding(route, filters=256, kernel_size=1, data_format=self.data_format)
        inputs = batch_norm(inputs, training=training, data_format=self.data_format)
        inputs = tf.nn.leaky_relu(inputs, alpha=_LEAKY_RELU)
        upsample_size = route2.get_shape().as_list()
        inputs = upsample(inputs, out_shape=upsample_size, data_format=self.data_format)
        axis = 1 if self.data_format == 'channels_first' else 3
        inputs = tf.concat([inputs, route2], axis=axis)
        route, inputs = yolo_convolution_block(inputs, filters=256, training=training, data_format=self.data_format)
        detect2 = yolo_layer(inputs, n_classes=self.n_classes, anchors=_ANCHORS[3:6], img_size=self.model_size, data_format=self.data_format)
        inputs = conv2d_fixed_padding(route, filters=128, kernel_size=1, data_format=self.data_format)
        inputs = batch_norm(inputs, training=training, data_format=self.data_format)
        inputs = tf.nn.leaky_relu(inputs, alpha=_LEAKY_RELU)
        upsample_size = route1.get_shape().as_list()
        inputs = upsample(inputs, out_shape=upsample_size, data_format=self.data_format)
        inputs = tf.concat([inputs, route1], axis=axis)
        route, inputs = yolo_convolution_block(inputs, filters=128, training=training, data_format=self.data_format)
        detect3 = yolo_layer(inputs, n_classes=self.n_classes, anchors=_ANCHORS[0:3], img_size=self.model_size, data_format=self.data_format)
        inputs = tf.concat([detect1, detect2, detect3], axis=1)
        inputs = build_boxes(inputs)
        boxes_dicts = non_max_suppression(inputs, n_classes=self.n_classes, max_output_size=self.max_output_size, iou_threshold=self.iou_threshold, confidence_threshold=self.confidence_threshold)
        return boxes_dicts