人工智能学习与实训笔记（二）：神经网络之图像分类问题

# 定义 SimpleNet 网络结构
import paddle
from paddle.nn import Conv2D, MaxPool2D, Linear
import paddle.nn.functional as F
# 多层卷积神经网络实现
class MNIST(paddle.nn.Layer):
     def __init__(self):
         super(MNIST, self).__init__()
         
         # 定义卷积层，输出特征通道out_channels设置为20，卷积核的大小kernel_size为5，卷积步长stride=1，padding=2
         self.conv1 = Conv2D(in_channels=1, out_channels=20, kernel_size=5, stride=1, padding=2)
         # 定义池化层，池化核的大小kernel_size为2，池化步长为2
         self.max_pool1 = MaxPool2D(kernel_size=2, stride=2)
         # 定义卷积层，输出特征通道out_channels设置为20，卷积核的大小kernel_size为5，卷积步长stride=1，padding=2
         self.conv2 = Conv2D(in_channels=20, out_channels=20, kernel_size=5, stride=1, padding=2)
         # 定义池化层，池化核的大小kernel_size为2，池化步长为2
         self.max_pool2 = MaxPool2D(kernel_size=2, stride=2)
         # 定义一层全连接层，输出维度是1
         self.fc = Linear(in_features=980, out_features=1)
         
    # 定义网络前向计算过程，卷积后紧接着使用池化层，最后使用全连接层计算最终输出
    # 卷积层激活函数使用Relu，全连接层不使用激活函数
     def forward(self, inputs):
         x = self.conv1(inputs)
         x = F.relu(x)
         x = self.max_pool1(x)
         x = self.conv2(x)
         x = F.relu(x)
         x = self.max_pool2(x)
         x = paddle.reshape(x, [x.shape[0], -1])
         x = self.fc(x)
         return x

import numpy as np
import cv2
from PIL import Image, ImageEnhance
import random
 
# 随机改变亮暗、对比度和颜色等
def random_distort(img):
    # 随机改变亮度
    def random_brightness(img, lower=0.5, upper=1.5):
        e = np.random.uniform(lower, upper)
        return ImageEnhance.Brightness(img).enhance(e)
    # 随机改变对比度
    def random_contrast(img, lower=0.5, upper=1.5):
        e = np.random.uniform(lower, upper)
        return ImageEnhance.Contrast(img).enhance(e)
    # 随机改变颜色
    def random_color(img, lower=0.5, upper=1.5):
        e = np.random.uniform(lower, upper)
        return ImageEnhance.Color(img).enhance(e)
 
    ops = [random_brightness, random_contrast, random_color]
    np.random.shuffle(ops)
 
    img = Image.fromarray(img)
    img = ops[0](img)
    img = ops[1](img)
    img = ops[2](img)
    img = np.asarray(img)
 
    return img
 
# 定义可视化函数，用于对比原图和图像增强的效果
import matplotlib.pyplot as plt
def visualize(srcimg, img_enhance):
    # 图像可视化
    plt.figure(num=2, figsize=(6,12))
    plt.subplot(1,2,1)
    plt.title('Src Image', color='#0000FF')
    plt.axis('off') # 不显示坐标轴
    plt.imshow(srcimg) # 显示原图片
 
    # 对原图做 随机改变亮暗、对比度和颜色等 数据增强
    srcimg_gtbox = records[0]['gt_bbox']
    srcimg_label = records[0]['gt_class']
 
    plt.subplot(1,2,2)
    plt.title('Enhance Image', color='#0000FF')
    plt.axis('off') # 不显示坐标轴
    plt.imshow(img_enhance)
 
 
image_path = records[0]['im_file']
print("read image from file {}".format(image_path))
srcimg = Image.open(image_path)
# 将PIL读取的图像转换成array类型
srcimg = np.array(srcimg)
 
# 对原图做 随机改变亮暗、对比度和颜色等 数据增强
img_enhance = random_distort(srcimg)
visualize(srcimg, img_enhance)

# 随机填充
def random_expand(img,
                  gtboxes,
                  max_ratio=4.,
                  fill=None,
                  keep_ratio=True,
                  thresh=0.5):
    if random.random() > thresh:
        return img, gtboxes
 
    if max_ratio < 1.0:
        return img, gtboxes
 
    h, w, c = img.shape
    ratio_x = random.uniform(1, max_ratio)
    if keep_ratio:
        ratio_y = ratio_x
    else:
        ratio_y = random.uniform(1, max_ratio)
    oh = int(h * ratio_y)
    ow = int(w * ratio_x)
    off_x = random.randint(0, ow - w)
    off_y = random.randint(0, oh - h)
 
    out_img = np.zeros((oh, ow, c))
    if fill and len(fill) == c:
        for i in range(c):
            out_img[:, :, i] = fill[i] * 255.0
 
    out_img[off_y:off_y + h, off_x:off_x + w, :] = img
    gtboxes[:, 0] = ((gtboxes[:, 0] * w) + off_x) / float(ow)
    gtboxes[:, 1] = ((gtboxes[:, 1] * h) + off_y) / float(oh)
    gtboxes[:, 2] = gtboxes[:, 2] / ratio_x
    gtboxes[:, 3] = gtboxes[:, 3] / ratio_y
 
    return out_img.astype('uint8'), gtboxes
 
 
# 对原图做 随机改变亮暗、对比度和颜色等 数据增强
srcimg_gtbox = records[0]['gt_bbox']
img_enhance, new_gtbox = random_expand(srcimg, srcimg_gtbox)
visualize(srcimg, img_enhance)

import numpy as np
 
def multi_box_iou_xywh(box1, box2):
    """
    In this case, box1 or box2 can contain multi boxes.
    Only two cases can be processed in this method:
       1, box1 and box2 have the same shape, box1.shape == box2.shape
       2, either box1 or box2 contains only one box, len(box1) == 1 or len(box2) == 1
    If the shape of box1 and box2 does not match, and both of them contain multi boxes, it will be wrong.
    """
    assert box1.shape[-1] == 4, "Box1 shape[-1] should be 4."
    assert box2.shape[-1] == 4, "Box2 shape[-1] should be 4."
 
 
    b1_x1, b1_x2 = box1[:, 0] - box1[:, 2] / 2, box1[:, 0] + box1[:, 2] / 2
    b1_y1, b1_y2 = box1[:, 1] - box1[:, 3] / 2, box1[:, 1] + box1[:, 3] / 2
    b2_x1, b2_x2 = box2[:, 0] - box2[:, 2] / 2, box2[:, 0] + box2[:, 2] / 2
    b2_y1, b2_y2 = box2[:, 1] - box2[:, 3] / 2, box2[:, 1] + box2[:, 3] / 2
 
    inter_x1 = np.maximum(b1_x1, b2_x1)
    inter_x2 = np.minimum(b1_x2, b2_x2)
    inter_y1 = np.maximum(b1_y1, b2_y1)
    inter_y2 = np.minimum(b1_y2, b2_y2)
    inter_w = inter_x2 - inter_x1
    inter_h = inter_y2 - inter_y1
    inter_w = np.clip(inter_w, a_min=0., a_max=None)
    inter_h = np.clip(inter_h, a_min=0., a_max=None)
 
    inter_area = inter_w * inter_h
    b1_area = (b1_x2 - b1_x1) * (b1_y2 - b1_y1)
    b2_area = (b2_x2 - b2_x1) * (b2_y2 - b2_y1)
 
    return inter_area / (b1_area + b2_area - inter_area)
 
def box_crop(boxes, labels, crop, img_shape):
    x, y, w, h = map(float, crop)
    im_w, im_h = map(float, img_shape)
 
    boxes = boxes.copy()
    boxes[:, 0], boxes[:, 2] = (boxes[:, 0] - boxes[:, 2] / 2) * im_w, (
        boxes[:, 0] + boxes[:, 2] / 2) * im_w
    boxes[:, 1], boxes[:, 3] = (boxes[:, 1] - boxes[:, 3] / 2) * im_h, (
        boxes[:, 1] + boxes[:, 3] / 2) * im_h
 
    crop_box = np.array([x, y, x + w, y + h])
    centers = (boxes[:, :2] + boxes[:, 2:]) / 2.0
    mask = np.logical_and(crop_box[:2] <= centers, centers <= crop_box[2:]).all(
        axis=1)
 
    boxes[:, :2] = np.maximum(boxes[:, :2], crop_box[:2])
    boxes[:, 2:] = np.minimum(boxes[:, 2:], crop_box[2:])
    boxes[:, :2] -= crop_box[:2]
    boxes[:, 2:] -= crop_box[:2]
 
    mask = np.logical_and(mask, (boxes[:, :2] < boxes[:, 2:]).all(axis=1))
    boxes = boxes * np.expand_dims(mask.astype('float32'), axis=1)
    labels = labels * mask.astype('float32')
    boxes[:, 0], boxes[:, 2] = (boxes[:, 0] + boxes[:, 2]) / 2 / w, (
        boxes[:, 2] - boxes[:, 0]) / w
    boxes[:, 1], boxes[:, 3] = (boxes[:, 1] + boxes[:, 3]) / 2 / h, (
        boxes[:, 3] - boxes[:, 1]) / h
 
    return boxes, labels, mask.sum()
 
# 随机裁剪
def random_crop(img,
                boxes,
                labels,
                scales=[0.3, 1.0],
                max_ratio=2.0,
                constraints=None,
                max_trial=50):
    if len(boxes) == 0:
        return img, boxes
 
    if not constraints:
        constraints = [(0.1, 1.0), (0.3, 1.0), (0.5, 1.0), (0.7, 1.0),
                       (0.9, 1.0), (0.0, 1.0)]
 
    img = Image.fromarray(img)
    w, h = img.size
    crops = [(0, 0, w, h)]
    for min_iou, max_iou in constraints:
        for _ in range(max_trial):
            scale = random.uniform(scales[0], scales[1])
            aspect_ratio = random.uniform(max(1 / max_ratio, scale * scale), \
                                          min(max_ratio, 1 / scale / scale))
            crop_h = int(h * scale / np.sqrt(aspect_ratio))
            crop_w = int(w * scale * np.sqrt(aspect_ratio))
            crop_x = random.randrange(w - crop_w)
            crop_y = random.randrange(h - crop_h)
            crop_box = np.array([[(crop_x + crop_w / 2.0) / w,
                                  (crop_y + crop_h / 2.0) / h,
                                  crop_w / float(w), crop_h / float(h)]])
 
            iou = multi_box_iou_xywh(crop_box, boxes)
            if min_iou <= iou.min() and max_iou >= iou.max():
                crops.append((crop_x, crop_y, crop_w, crop_h))
                break
 
    while crops:
        crop = crops.pop(np.random.randint(0, len(crops)))
        crop_boxes, crop_labels, box_num = box_crop(boxes, labels, crop, (w, h))
        if box_num < 1:
            continue
        img = img.crop((crop[0], crop[1], crop[0] + crop[2],
                        crop[1] + crop[3])).resize(img.size, Image.LANCZOS)
        img = np.asarray(img)
        return img, crop_boxes, crop_labels
    img = np.asarray(img)
    return img, boxes, labels
 
 
# 对原图做 随机改变亮暗、对比度和颜色等 数据增强
srcimg_gtbox = records[0]['gt_bbox']
srcimg_label = records[0]['gt_class']
 
img_enhance, new_labels, mask = random_crop(srcimg, srcimg_gtbox, srcimg_label)
visualize(srcimg, img_enhance)
 

# 随机缩放
def random_interp(img, size, interp=None):
    interp_method = [
        cv2.INTER_NEAREST,
        cv2.INTER_LINEAR,
        cv2.INTER_AREA,
        cv2.INTER_CUBIC,
        cv2.INTER_LANCZOS4,
    ]
    if not interp or interp not in interp_method:
        interp = interp_method[random.randint(0, len(interp_method) - 1)]
    h, w, _ = img.shape
    im_scale_x = size / float(w)
    im_scale_y = size / float(h)
    img = cv2.resize(
        img, None, None, fx=im_scale_x, fy=im_scale_y, interpolation=interp)
    return img
 
# 对原图做 随机缩放
img_enhance = random_interp(srcimg, 640)
visualize(srcimg, img_enhance)

# 随机翻转
def random_flip(img, gtboxes, thresh=0.5):
    if random.random() > thresh:
        img = img[:, ::-1, :]
        gtboxes[:, 0] = 1.0 - gtboxes[:, 0]
    return img, gtboxes
 
 
# 对原图做 随机改变亮暗、对比度和颜色等 数据增强
img_enhance, box_enhance = random_flip(srcimg, srcimg_gtbox)
visualize(srcimg, img_enhance)

# 随机打乱真实框排列顺序
def shuffle_gtbox(gtbox, gtlabel):
    gt = np.concatenate(
        [gtbox, gtlabel[:, np.newaxis]], axis=1)
    idx = np.arange(gt.shape[0])
    np.random.shuffle(idx)
    gt = gt[idx, :]
    return gt[:, :4], gt[:, 4]