各位客官实在是抱歉，最近开始上班了，导致没时间更新博客，好不容易有个周末，来把没有写完的写上。
这个是我在GitHub上下载的一个master，具体链接不记得了，下载完结构如下图
大家自己在GitHub上找一找，这个代码有很多大神都已经写完了，先说一说需要改动的地方吧。
我们来依次介绍，font就是个放字体文件的文件夹，要是想要简体中文的话自己在网上下载个文件就可以了，放在yolo.py文件里的154行就可以了、
下一个文件夹log这个是用来存放训练的模型的，这个大神的代码保存的是**.h5模型，所以用的就是tensorflow中的keras进行的训练。接下来是model_data文件夹
把这里的文本改成你要检测的类别，比如说我的，就改成了DuanSha、DaiSha、WuZi、PoDong、MianQiu、TuoSha 这几类
再然后是VOCdevikt**文件夹，这个就是上面做的数据存放的文件夹，里面就是标准VOC格式数据集的内容
来一条华丽的分割线
接下来就是重点了。先来介绍yolov3文件夹，先是 model.py 文件。我下载的这个代码中，作者已经注释的很全面了，下面全放上去，让大家伙瞅瞅。我把tiny的框架给删除了，要用咱就用多的，哈哈哈
"""YOLO_v3 Model Defined in Keras."""
from functools import wraps
import numpy as np
import tensorflow as tf
from keras import backend as K
from keras.layers import Conv2D, Add, ZeroPadding2D, UpSampling2D, Concatenate, MaxPooling2D
from keras.layers.advanced_activations import LeakyReLU
from keras.layers.normalization import BatchNormalization
from keras.models import Model
from keras.regularizers import l2
from yolov3.utils import compose
@wraps(Conv2D)
def DarknetConv2D(*args, **kwargs):
"""Wrapper to set Darknet parameters for Convolution2D."""
darknet_conv_kwargs = {'kernel_regularizer': l2(5e-4)}
darknet_conv_kwargs['padding'] = 'valid' if kwargs.get('strides')==(2,2) else 'same'
darknet_conv_kwargs.update(kwargs)
return Conv2D(*args, **darknet_conv_kwargs)
def DarknetConv2D_BN_Leaky(*args, **kwargs):
"""Darknet Convolution2D followed by BatchNormalization and LeakyReLU."""
no_bias_kwargs = {'use_bias': False}
no_bias_kwargs.update(kwargs)
return compose(
DarknetConv2D(*args, **no_bias_kwargs),
BatchNormalization(),
LeakyReLU(alpha=0.1))
def resblock_body(x, num_filters, num_blocks):
'''A series of resblocks starting with a downsampling Convolution2D'''
# Darknet uses left and top padding instead of 'same' mode
x = ZeroPadding2D(((1,0),(1,0)))(x)
x = DarknetConv2D_BN_Leaky(num_filters, (3,3), strides=(2,2))(x)
for i in range(num_blocks):
y = compose(
DarknetConv2D_BN_Leaky(num_filters//2, (1,1)),
DarknetConv2D_BN_Leaky(num_filters, (3,3)))(x)
x = Add()([x,y])
return x
def darknet_body(x):
'''Darknent body having 52 Convolution2D layers'''
x = DarknetConv2D_BN_Leaky(32, (3,3))(x)
x = resblock_body(x, 64, 1)
x = resblock_body(x, 128, 2)
x = resblock_body(x, 256, 8)
x = resblock_body(x, 512, 8)
x = resblock_body(x, 1024, 4)
return x
def make_last_layers(x, num_filters, out_filters):
'''6 Conv2D_BN_Leaky layers followed by a Conv2D_linear layer'''
x = compose(
DarknetConv2D_BN_Leaky(num_filters, (1,1)),
DarknetConv2D_BN_Leaky(num_filters*2, (3,3)),
DarknetConv2D_BN_Leaky(num_filters, (1,1)),
DarknetConv2D_BN_Leaky(num_filters*2, (3,3)),
DarknetConv2D_BN_Leaky(num_filters, (1,1)))(x)
y = compose(
DarknetConv2D_BN_Leaky(num_filters*2, (3,3)),
DarknetConv2D(out_filters, (1,1)))(x)
return x, y
def yolo_body(inputs, num_anchors, num_classes):
"""Create YOLO_V3 model CNN body in Keras."""
darknet = Model(inputs, darknet_body(inputs))
x, y1 = make_last_layers(darknet.output, 512, num_anchors*(num_classes+5))
x = compose(
DarknetConv2D_BN_Leaky(256, (1,1)),
UpSampling2D(2))(x)
x = Concatenate()([x,darknet.layers[152].output])
x, y2 = make_last_layers(x, 256, num_anchors*(num_classes+5))
x = compose(
DarknetConv2D_BN_Leaky(128, (1,1)),
UpSampling2D(2))(x)
x = Concatenate()([x,darknet.layers[92].output])
x, y3 = make_last_layers(x, 128, num_anchors*(num_classes+5))
return Model(inputs, [y1,y2,y3])
def yolo_head(feats, anchors, num_classes, input_shape, calc_loss=False):
"""Convert final layer features to bounding box parameters."""
# feats，即：feature maps
num_anchors = len(anchors)
# Reshape to batch, height, width, num_anchors, box_params.
anchors_tensor = K.reshape(K.constant(anchors), [1, 1, 1, num_anchors, 2])
grid_shape = K.shape(feats)[1:3] # # height, width #13x13或26x26或52x5
# 通过arange、reshape、tile的组合，根据grid_shape(13x13、26x26或52x52）创建y轴的0~N-1的组合grid_y，
# 再创建x轴的0~N-1的组合grid_x，将两者拼接concatenate，形成NxN的grid(13x13、26x26或52x52）
grid_y = K.tile(K.reshape(K.arange(0, stop=grid_shape[0]), [-1, 1, 1, 1]),
[1, grid_shape[1], 1, 1])
grid_x = K.tile(K.reshape(K.arange(0, stop=grid_shape[1]), [1, -1, 1, 1]),
[grid_shape[0], 1, 1, 1])
grid = K.concatenate([grid_x, grid_y])
grid = K.cast(grid, K.dtype(feats))
# 从待处理的feature map的最后一维数据中，先将num_anchors这个维度与num_classes+5这个维度的数据分离，
# 再取出4个框值tx、ty（最后一维数据的0:1）、tw和th（最后一维数据的2:3）
feats = K.reshape(
feats, [-1, grid_shape[0], grid_shape[1], num_anchors, num_classes + 5])
# Adjust preditions to each spatial grid point and anchor size.
# 用sigmoid()函数计算目标框的中心点box_xy，用exp()函数计算目标框的宽和高box_wh
# 使用特征图尺寸（如：13x13、26x26或52x52）在水平x、垂直y两个维度对box_xy进行归一化，确定目标框的中心点的相对位置
# 使用标准图片尺寸（416x416）在宽和高两个维度对box_wh
# （因为，3组9个anchor box是基于416x416尺寸定义的）进行归一化，确定目标框的高和宽的相对位置
box_xy = (K.sigmoid(feats[..., :2]) + grid) / K.cast(grid_shape[::-1], K.dtype(feats))
box_wh = K.exp(feats[..., 2:4]) * anchors_tensor / K.cast(input_shape[::-1], K.dtype(feats))
# 用sigmoid()函数计算目标框的置信度box_confidence
box_confidence = K.sigmoid(feats[..., 4:5])
# 用sigmoid()函数计算目标框的类别置信度box_class_probs
box_class_probs = K.sigmoid(feats[..., 5:])
if calc_loss == True:
return grid, feats, box_xy, box_wh
return box_xy, box_wh, box_confidence, box_class_probs
def yolo_correct_boxes(box_xy, box_wh, input_shape, image_shape):
'''Get corrected boxes'''
# 将box_xy, box_wh转换为输入图片上的真实坐标，输出boxes是框的左下、右上两个坐标(y_min, x_min, y_max, x_max)
# np.array[i:j:s]，当s<0时，i缺省时，默认为-1；j缺省时，默认为-len(a)-1；所以array[::-1]相当于array[-1:-len(a)-1:-1]，
# 也就是从最后一个元素到第一个元素复制一遍，即倒序
box_yx = box_xy[..., ::-1]
box_hw = box_wh[..., ::-1]
input_shape = K.cast(input_shape, K.dtype(box_yx))
image_shape = K.cast(image_shape, K.dtype(box_yx))
new_shape = K.round(image_shape * K.min(input_shape/image_shape))
offset = (input_shape-new_shape)/2./input_shape
scale = input_shape/new_shape
box_yx = (box_yx - offset) * scale
box_hw *= scale
box_mins = box_yx - (box_hw / 2.)
box_maxes = box_yx + (box_hw / 2.)
boxes = K.concatenate([
box_mins[..., 0:1], # y_min
box_mins[..., 1:2], # x_min
box_maxes[..., 0:1], # y_max
box_maxes[..., 1:2] # x_max
])
# Scale boxes back to original image shape.
boxes *= K.concatenate([image_shape, image_shape])
return boxes
def yolo_boxes_and_scores(feats, anchors, num_classes, input_shape, image_shape):
'''Process Conv layer output'''
# feats：需要处理的featue map
# shape：(?,13,13,255)，(?,26,26,255)或(?,52,52,255)
# anchors：每层对应的3个anchor box
# num_classes：类别数（80）
# input_shape:（416,416）
# image_shape：图像尺寸
box_xy, box_wh, box_confidence, box_class_probs = yolo_head(feats,
anchors, num_classes, input_shape)
boxes = yolo_correct_boxes(box_xy, box_wh, input_shape, image_shape)
boxes = K.reshape(boxes, [-1, 4])#形成框的列表boxes（?, 4)
box_scores = box_confidence * box_class_probs #框的得分=框的置信度x类别置信度
box_scores = K.reshape(box_scores, [-1, num_classes]) #形成框的得分列表box_scores（?, 80)
return boxes, box_scores
def yolo_eval(yolo_outputs,
anchors,
num_classes,
image_shape,
max_boxes=20,#每张图每类最多检测到20个框
score_threshold=.6,
iou_threshold=.5):
"""Evaluate YOLO model on given input and return filtered boxes."""
#将anchor_box分为3组，分别分配给13x13、26x26、52x52等3个yolo_model输出的feature map
num_layers = len(yolo_outputs)
anchor_mask = [[6,7,8], [3,4,5], [0,1,2]] if num_layers==3 else [[3,4,5], [1,2,3]] # 默认设置
input_shape = K.shape(yolo_outputs[0])[1:3] * 32
boxes = []
box_scores = []
#分别对3个feature map运行
for l in range(num_layers):
_boxes, _box_scores = yolo_boxes_and_scores(yolo_outputs[l],
anchors[anchor_mask[l]], num_classes, input_shape, image_shape)
boxes.append(_boxes)
box_scores.append(_box_scores)
#将运算得到的目标框用concatenate()函数拼接为（?, 4)的元组，将目标框的置信度拼接为(?,1)的元组
boxes = K.concatenate(boxes, axis=0)
box_scores = K.concatenate(box_scores, axis=0)
#计算MASK掩码，过滤小于score阈值的值，只保留大于阈值的值
mask = box_scores >= score_threshold
max_boxes_tensor = K.constant(max_boxes, dtype='int32')
boxes_ = []
scores_ = []
classes_ = []
for c in range(num_classes):
# TODO: use keras backend instead of tf.
class_boxes = tf.boolean_mask(boxes, mask[:, c])#通过掩码MASK和类别C筛选框boxes
class_box_scores = tf.boolean_mask(box_scores[:, c], mask[:, c])#通过掩码MASK和类别C筛选scores
nms_index = tf.image.non_max_suppression(
class_boxes, class_box_scores, max_boxes_tensor, iou_threshold=iou_threshold)
#运行非极大抑制non_max_suppression（），每类最多检测20个框
#K.gather:根据索引nms_index选择class_boxes和class_box_scores，标出选出的框的类别classes
class_boxes = K.gather(class_boxes, nms_index)
class_box_scores = K.gather(class_box_scores, nms_index)
classes = K.ones_like(class_box_scores, 'int32') * c
boxes_.append(class_boxes)
scores_.append(class_box_scores)
classes_.append(classes)
#用concatenate()函数把选出的class_boxes、class_box_scores和classes拼接，形成(?,4)、(?,1)和(?,80)的元组返回
boxes_ = K.concatenate(boxes_, axis=0)
scores_ = K.concatenate(scores_, axis=0)
classes_ = K.concatenate(classes_, axis=0)
return boxes_, scores_, classes_
def preprocess_true_boxes(true_boxes, input_shape, anchors, num_classes):
'''Preprocess true boxes to training input format
Parameters
----------
true_boxes: array, shape=(m, T, 5)
Absolute x_min, y_min, x_max, y_max, class_id relative to input_shape.
input_shape: array-like, hw, multiples of 32
anchors: array, shape=(N, 2), wh
num_classes: integer
Returns
-------
y_true: list of array, shape like yolo_outputs, xywh are reletive value
'''
assert (true_boxes[..., 4]<num_classes).all(), 'class id must be less than num_classes'
num_layers = len(anchors)//3 # default setting
anchor_mask = [[6,7,8], [3,4,5], [0,1,2]] if num_layers==3 else [[3,4,5], [1,2,3]]
true_boxes = np.array(true_boxes, dtype='float32')
input_shape = np.array(input_shape, dtype='int32')
boxes_xy = (true_boxes[..., 0:2] + true_boxes[..., 2:4]) // 2
boxes_wh = true_boxes[..., 2:4] - true_boxes[..., 0:2]
true_boxes[..., 0:2] = boxes_xy/input_shape[::-1]
true_boxes[..., 2:4] = boxes_wh/input_shape[::-1]
m = true_boxes.shape[0]
grid_shapes = [input_shape//{0:32, 1:16, 2:8}[l] for l in range(num_layers)]
y_true = [np.zeros((m,grid_shapes[l][0],grid_shapes[l][1],len(anchor_mask[l]),5+num_classes),
dtype='float32') for l in range(num_layers)]
# Expand dim to apply broadcasting.
anchors = np.expand_dims(anchors, 0)
anchor_maxes = anchors / 2.
anchor_mins = -anchor_maxes
valid_mask = boxes_wh[..., 0]>0
for b in range(m):
# Discard zero rows.
wh = boxes_wh[b, valid_mask[b]]
if len(wh)==0: continue
# Expand dim to apply broadcasting.
wh = np.expand_dims(wh, -2)
box_maxes = wh / 2.
box_mins = -box_maxes
intersect_mins = np.maximum(box_mins, anchor_mins)
intersect_maxes = np.minimum(box_maxes, anchor_maxes)
intersect_wh = np.maximum(intersect_maxes - intersect_mins, 0.)
intersect_area = intersect_wh[..., 0] * intersect_wh[..., 1]
box_area = wh[..., 0] * wh[..., 1]
anchor_area = anchors[..., 0] * anchors[..., 1]
iou = intersect_area / (box_area + anchor_area - intersect_area)
# Find best anchor for each true box
best_anchor = np.argmax(iou, axis=-1)
for t, n in enumerate(best_anchor):
for l in range(num_layers):
if n in anchor_mask[l]:
i = np.floor(true_boxes[b,t,0]*grid_shapes[l][1]).astype('int32')
j = np.floor(true_boxes[b,t,1]*grid_shapes[l][0]).astype('int32')
k = anchor_mask[l].index(n)
c = true_boxes[b,t, 4].astype('int32')
y_true[l][b, j, i, k, 0:4] = true_boxes[b,t, 0:4]
y_true[l][b, j, i, k, 4] = 1
y_true[l][b, j, i, k, 5+c] = 1
return y_true
def box_iou(b1, b2):
'''Return iou tensor
Parameters
----------
b1: tensor, shape=(i1,...,iN, 4), xywh
b2: tensor, shape=(j, 4), xywh
Returns
-------
iou: tensor, shape=(i1,...,iN, j)
'''
# Expand dim to apply broadcasting.
b1 = K.expand_dims(b1, -2)
b1_xy = b1[..., :2]
b1_wh = b1[..., 2:4]
b1_wh_half = b1_wh/2.
b1_mins = b1_xy - b1_wh_half
b1_maxes = b1_xy + b1_wh_half
# Expand dim to apply broadcasting.
b2 = K.expand_dims(b2, 0)
b2_xy = b2[..., :2]
b2_wh = b2[..., 2:4]
b2_wh_half = b2_wh/2.
b2_mins = b2_xy - b2_wh_half
b2_maxes = b2_xy + b2_wh_half
intersect_mins = K.maximum(b1_mins, b2_mins)
intersect_maxes = K.minimum(b1_maxes, b2_maxes)
intersect_wh = K.maximum(intersect_maxes - intersect_mins, 0.)
intersect_area = intersect_wh[..., 0] * intersect_wh[..., 1]
b1_area = b1_wh[..., 0] * b1_wh[..., 1]
b2_area = b2_wh[..., 0] * b2_wh[..., 1]
iou = intersect_area / (b1_area + b2_area - intersect_area)
return iou
def yolo_loss(args, anchors, num_classes, ignore_thresh=.5, print_loss=False):
'''Return yolo_loss tensor
Parameters
----------
yolo_outputs: list of tensor, the output of yolo_body or tiny_yolo_body
y_true: list of array, the output of preprocess_true_boxes
anchors: array, shape=(N, 2), wh
num_classes: integer
ignore_thresh: float, the iou threshold whether to ignore object confidence loss
Returns
-------
loss: tensor, shape=(1,)
'''
num_layers = len(anchors)//3 # default setting
yolo_outputs = args[:num_layers]
y_true = args[num_layers:]
anchor_mask = [[6,7,8], [3,4,5], [0,1,2]] if num_layers==3 else [[3,4,5], [1,2,3]]
input_shape = K.cast(K.shape(yolo_outputs[0])[1:3] * 32, K.dtype(y_true[0]))
grid_shapes = [K.cast(K.shape(yolo_outputs[l])[1:3], K.dtype(y_true[0])) for l in range(num_layers)]
loss = 0
m = K.shape(yolo_outputs[0])[0] # batch size, tensor
mf = K.cast(m, K.dtype(yolo_outputs[0]))
for l in range(num_layers):
object_mask = y_true[l][..., 4:5]
true_class_probs = y_true[l][..., 5:]
grid, raw_pred, pred_xy, pred_wh = yolo_head(yolo_outputs[l],
anchors[anchor_mask[l]], num_classes, input_shape, calc_loss=True)
pred_box = K.concatenate([pred_xy, pred_wh])
# Darknet raw box to calculate loss.
raw_true_xy = y_true[l][..., :2]*grid_shapes[l][::-1] - grid
raw_true_wh = K.log(y_true[l][..., 2:4] / anchors[anchor_mask[l]] * input_shape[::-1])
raw_true_wh = K.switch(object_mask, raw_true_wh, K.zeros_like(raw_true_wh)) # avoid log(0)=-inf
box_loss_scale = 2 - y_true[l][...,2:3]*y_true[l][...,3:4]
# Find ignore mask, iterate over each of batch.
ignore_mask = tf.TensorArray(K.dtype(y_true[0]), size=1, dynamic_size=True)
object_mask_bool = K.cast(object_mask, 'bool')
def loop_body(b, ignore_mask):
true_box = tf.boolean_mask(y_true[l][b,...,0:4], object_mask_bool[b,...,0])
iou = box_iou(pred_box[b], true_box)
best_iou = K.max(iou, axis=-1)
ignore_mask = ignore_mask.write(b, K.cast(best_iou<ignore_thresh, K.dtype(true_box)))
return b+1, ignore_mask
_, ignore_mask = K.control_flow_ops.while_loop(lambda b,*args: b<m, loop_body, [0, ignore_mask])
ignore_mask = ignore_mask.stack()
ignore_mask = K.expand_dims(ignore_mask, -1)
# K.binary_crossentropy is helpful to avoid exp overflow.
xy_loss = object_mask * box_loss_scale * K.binary_crossentropy(raw_true_xy, raw_pred[...,0:2], from_logits=True)
wh_loss = object_mask * box_loss_scale * 0.5 * K.square(raw_true_wh-raw_pred[...,2:4])
confidence_loss = object_mask * K.binary_crossentropy(object_mask, raw_pred[...,4:5], from_logits=True)+ \
(1-object_mask) * K.binary_crossentropy(object_mask, raw_pred[...,4:5], from_logits=True) * ignore_mask
class_loss = object_mask * K.binary_crossentropy(true_class_probs, raw_pred[...,5:], from_logits=True)
xy_loss = K.sum(xy_loss) / mf
wh_loss = K.sum(wh_loss) / mf
confidence_loss = K.sum(confidence_loss) / mf
class_loss = K.sum(class_loss) / mf
loss += xy_loss + wh_loss + confidence_loss + class_loss
if print_loss:
loss = tf.Print(loss, [loss, xy_loss, wh_loss, confidence_loss, class_loss, K.sum(ignore_mask)], message='loss: ')
return loss
然后是utils.py文件，这两个文件都不需要改啥玩意，直接复制粘贴就可以了。
"""Miscellaneous utility functions."""
from functools import reduce
from PIL import Image
import numpy as np
from matplotlib.colors import rgb_to_hsv, hsv_to_rgb
def compose(*funcs):
"""Compose arbitrarily many functions, evaluated left to right.
Reference: https://mathieularose.com/function-composition-in-python/
"""
# return lambda x: reduce(lambda v, f: f(v), funcs, x)
if funcs:
return reduce(lambda f, g: lambda *a, **kw: g(f(*a, **kw)), funcs)
else:
raise ValueError('Composition of empty sequence not supported.')
def letterbox_image(image, size):
'''resize image with unchanged aspect ratio using padding'''
# 先生成一个用“绝对灰”R128-G128-B128“填充的416x416新图片，然后用按比例缩放（采样方法：BICUBIC双三次插值）后的输入图片粘贴，
# 粘贴不到的部分保留为灰色
iw, ih = image.size
w, h = size
scale = min(w/iw, h/ih)
nw = int(iw*scale)
nh = int(ih*scale)
image = image.resize((nw,nh), Image.BICUBIC)
new_image = Image.new('RGB', size, (128,128,128))
new_image.paste(image, ((w-nw)//2, (h-nh)//2))
return new_image
def rand(a=0, b=1):
return np.random.rand()*(b-a) + a
def get_random_data(annotation_line, input_shape, random=True, max_boxes=20, jitter=.3, hue=.1, sat=1.5, val=1.5, proc_img=True):
'''random preprocessing for real-time data augmentation'''
line = annotation_line.split()
print(line[0])
image = Image.open(line[0])
iw, ih = image.size
print(iw, ih)
h, w = input_shape
box = np.array([np.array(list(map(int,box.split(',')))) for box in line[1:]])
if not random:
# resize image
scale = min(w/iw, h/ih)
nw = int(iw*scale)
nh = int(ih*scale)
dx = (w-nw)//2
dy = (h-nh)//2
image_data=0
if proc_img:
image = image.resize((nw,nh), Image.BICUBIC)
new_image = Image.new('RGB', (w,h), (128,128,128))
new_image.paste(image, (dx, dy))
image_data = np.array(new_image)/255.
# correct boxes
box_data = np.zeros((max_boxes,5))
if len(box)>0:
np.random.shuffle(box)
if len(box)>max_boxes: box = box[:max_boxes]
box[:, [0,2]] = box[:, [0,2]]*scale + dx
box[:, [1,3]] = box[:, [1,3]]*scale + dy
box_data[:len(box)] = box
return image_data, box_data
# resize image
new_ar = w/h * rand(1-jitter,1+jitter)/rand(1-jitter,1+jitter)
scale = rand(.25, 2)
if new_ar < 1:
nh = int(scale*h)
nw = int(nh*new_ar)
else:
nw = int(scale*w)
nh = int(nw/new_ar)
image = image.resize((nw,nh), Image.BICUBIC)
# place image
dx = int(rand(0, w-nw))
dy = int(rand(0, h-nh))
new_image = Image.new('RGB', (w,h), (128,128,128))
new_image.paste(image, (dx, dy))
image = new_image
# flip image or not
flip = rand()<.5
if flip: image = image.transpose(Image.FLIP_LEFT_RIGHT)
# distort image
hue = rand(-hue, hue)
sat = rand(1, sat) if rand()<.5 else 1/rand(1, sat)
val = rand(1, val) if rand()<.5 else 1/rand(1, val)
x = rgb_to_hsv(np.array(image)/255.)
x[..., 0] += hue
x[..., 0][x[..., 0]>1] -= 1
x[..., 0][x[..., 0]<0] += 1
x[..., 1] *= sat
x[..., 2] *= val
x[x>1] = 1
x[x<0] = 0
image_data = hsv_to_rgb(x) # numpy array, 0 to 1
# correct boxes
box_data = np.zeros((max_boxes,5))
if len(box)>0:
np.random.shuffle(box)
box[:, [0,2]] = box[:, [0,2]]*nw/iw + dx
box[:, [1,3]] = box[:, [1,3]]*nh/ih + dy
if flip: box[:, [0,2]] = w - box[:, [2,0]]
box[:, 0:2][box[:, 0:2]<0] = 0
box[:, 2][box[:, 2]>w] = w
box[:, 3][box[:, 3]>h] = h
box_w = box[:, 2] - box[:, 0]
box_h = box[:, 3] - box[:, 1]
box = box[np.logical_and(box_w>1, box_h>1)] # discard invalid box
if len(box)>max_boxes: box = box[:max_boxes]
box_data[:len(box)] = box
return image_data, box_data
接下来是最主要的配置文件的修改。yolov3_defect.cfg , 这里你Ctrl+f 搜索 yolo 就会找到要改的地方，其中 filters=3（分类数+5）*，classes就是你要分类的个数，random改不改都可以，你要是觉得你电脑能行，你就改成1，不行的话就拉到。
[net]
# Testing
batch=1
subdivisions=1
# Training
# batch=64
# subdivisions=16
width=416
height=416
channels=3
momentum=0.9
decay=0.0005
angle=0
saturation = 1.5
exposure = 1.5
hue=.1
learning_rate=0.001
burn_in=1000
max_batches = 500200
policy=steps
steps=400000,450000
scales=.1,.1
[convolutional]
batch_normalize=1
filters=32
size=3
stride=1
pad=1
activation=leaky
# Downsample
[convolutional]
batch_normalize=1
filters=64
size=3
stride=2
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=32
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=64
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
# Downsample
[convolutional]
batch_normalize=1
filters=128
size=3
stride=2
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=64
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=128
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=64
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=128
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
# Downsample
[convolutional]
batch_normalize=1
filters=256
size=3
stride=2
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
# Downsample
[convolutional]
batch_normalize=1
filters=512
size=3
stride=2
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=512
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=512
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=512
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=512
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=512
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=512
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=512
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=512
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
# Downsample
[convolutional]
batch_normalize=1
filters=1024
size=3
stride=2
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=1024
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=1024
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=1024
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=1024
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
######################
[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=1024
activation=leaky
[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=1024
activation=leaky
[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=1024
activation=leaky
[convolutional]
size=1
stride=1
pad=1
filters=33
activation=linear
[yolo]
mask = 6,7,8
anchors = 10,13, 16,30, 33,23, 30,61, 62,45, 59,119, 116,90, 156,198, 373,326
classes=6
num=9
jitter=.3
ignore_thresh = .5
truth_thresh = 1
random=0
[route]
layers = -4
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[upsample]
stride=2
[route]
layers = -1, 61
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=512
activation=leaky
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=512
activation=leaky
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=512
activation=leaky
[convolutional]
size=1
stride=1
pad=1
filters=33
activation=linear
[yolo]
mask = 3,4,5
anchors = 10,13, 16,30, 33,23, 30,61, 62,45, 59,119, 116,90, 156,198, 373,326
classes=6
num=9
jitter=.3
ignore_thresh = .5
truth_thresh = 1
random=0
[route]
layers = -4
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[upsample]
stride=2
[route]
layers = -1, 36
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=256
activation=leaky
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=256
activation=leaky
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=256
activation=leaky
[convolutional]
size=1
stride=1
pad=1
filters=33
activation=linear
[yolo]
mask = 0,1,2
anchors = 10,13, 16,30, 33,23, 30,61, 62,45, 59,119, 116,90, 156,198, 373,326
classes=6
num=9
jitter=.3
ignore_thresh = .5
truth_thresh = 1
random=0
接下来就是重中之重的 train.py 文件了。这个改个文件读取路径就可以了，要是训练效果不好的的话，你得在其他文件里该参数。
"""
Retrain the YOLO model for your own dataset.
"""
import numpy as np
import keras.backend as K
from keras.layers import Input, Lambda
from keras.models import Model
from keras.callbacks import TensorBoard, ModelCheckpoint, EarlyStopping
from yolov3.model import preprocess_true_boxes, yolo_body, tiny_yolo_body, yolo_loss
from yolov3.utils import get_random_data
def _main():
annotation_path = '2020_train.txt'
log_dir = 'logs/000/'
classes_path = 'model_data/voc_classes_defect.txt'
anchors_path = 'model_data/yolo_anchors.txt'
class_names = get_classes(classes_path)
anchors = get_anchors(anchors_path)
input_shape = (416,416) # multiple of 32, hw
model = create_model(input_shape, anchors, len(class_names) )
train(model, annotation_path, input_shape, anchors, len(class_names), log_dir=log_dir)
def train(model, annotation_path, input_shape, anchors, num_classes, log_dir='logs/'):
model.compile(optimizer='adam', loss={
'yolo_loss': lambda y_true, y_pred: y_pred})
logging = TensorBoard(log_dir=log_dir)
checkpoint = ModelCheckpoint(log_dir + "ep{epoch:03d}-loss{loss:.3f}-val_loss{val_loss:.3f}.h5",
monitor='val_loss', save_weights_only=True, save_best_only=True, period=1)
batch_size = 10
val_split = 0.1
with open(annotation_path) as f:
lines = f.readlines()
np.random.shuffle(lines)
num_val = int(len(lines)*val_split)
num_train = len(lines) - num_val
print('Train on {} samples, val on {} samples, with batch size {}.'.format(num_train, num_val, batch_size))
model.fit_generator(data_generator_wrap(lines[:num_train], batch_size, input_shape, anchors, num_classes),
steps_per_epoch=max(1, num_train//batch_size),
validation_data=data_generator_wrap(lines[num_train:], batch_size, input_shape, anchors, num_classes),
validation_steps=max(1, num_val//batch_size),
epochs=500,
initial_epoch=0)
model.save_weights(log_dir + 'trained_weights.h5')
def get_classes(classes_path):
with open(classes_path) as f:
class_names = f.readlines()
class_names = [c.strip() for c in class_names]
return class_names
def get_anchors(anchors_path):
with open(anchors_path) as f:
anchors = f.readline()
anchors = [float(x) for x in anchors.split(',')]
return np.array(anchors).reshape(-1, 2)
def create_model(input_shape, anchors, num_classes, load_pretrained=False, freeze_body=False,
weights_path='model_data/yolo_weights.h5'):
K.clear_session() # get a new session
image_input = Input(shape=(None, None, 3))
h, w = input_shape
num_anchors = len(anchors)
y_true = [Input(shape=(h//{0:32, 1:16, 2:8}[l], w//{0:32, 1:16, 2:8}[l], \
num_anchors//3, num_classes+5)) for l in range(3)]
model_body = yolo_body(image_input, num_anchors//3, num_classes)
print('Create YOLOv3 model with {} anchors and {} classes.'.format(num_anchors, num_classes))
if load_pretrained:
model_body.load_weights(weights_path, by_name=True, skip_mismatch=True)
print('Load weights {}.'.format(weights_path))
if freeze_body:
# Do not freeze 3 output layers.
num = len(model_body.layers)-7
for i in range(num): model_body.layers[i].trainable = False
print('Freeze the first {} layers of total {} layers.'.format(num, len(model_body.layers)))
model_loss = Lambda(yolo_loss, output_shape=(1,), name='yolo_loss',
arguments={'anchors': anchors, 'num_classes': num_classes, 'ignore_thresh': 0.5})(
[*model_body.output, *y_true])
model = Model([model_body.input, *y_true], model_loss)
return model
def data_generator(annotation_lines, batch_size, input_shape, anchors, num_classes):
n = len(annotation_lines)
np.random.shuffle(annotation_lines)
i = 0
while True:
image_data = []
box_data = []
for b in range(batch_size):
i %= n
image, box = get_random_data(annotation_lines[i], input_shape, random=True)
image_data.append(image)
box_data.append(box)
i += 1
image_data = np.array(image_data)
box_data = np.array(box_data)
y_true = preprocess_true_boxes(box_data, input_shape, anchors, num_classes)
yield [image_data, *y_true], np.zeros(batch_size)
def data_generator_wrap(annotation_lines, batch_size, input_shape, anchors, num_classes):
n = len(annotation_lines)
if n==0 or batch_size<=0: return None
return data_generator(annotation_lines, batch_size, input_shape, anchors, num_classes)
if __name__ == '__main__':
_main()
我就是运行之后电脑扛不住就完蛋了，哈哈哈。
然后是我们这个yolov3的主体文件了，也就是 yolo.py 文件
# -*- coding: utf-8 -*-
"""
Class definition of YOLO_v3 style detection model on image and video
"""
import colorsys
import os
from timeit import default_timer as timer
import numpy as np
from keras import backend as K
from keras.models import load_model
from keras.layers import Input
from PIL import Image, ImageFont, ImageDraw
from yolov3.model import yolo_eval, yolo_body, tiny_yolo_body
from yolov3.utils import letterbox_image
import os
from keras.utils import multi_gpu_model
class YOLO(object):
'''
"model_path": 'model_data/yolo.h5', #已经训练好的模型
"anchors_path": 'model_data/yolo_anchors.txt', #通过聚类算法得到的3组9个anchor box，分别用于13x13、26x26、52x52的feature map
"classes_path": 'model_data/coco.names', #可识别的COCO类别列表，一共80个
"score" : 0.3, #框置信度阈值阈值，小于阈值则目标框被抛弃
"iou" : 0.45, #IOU（Intersection over Union）阈值，大于阈值的重叠框被删除
"model_image_size" : (416, 416), #输入图片的“标准尺寸”，不同于这个尺寸的输入会首先调整到标准大小
"gpu_num" : 1, #GPU数量，通常是指Nvidia的GPU
'''
_defaults = {
"model_path": 'D:\Pycharm\object_defect\Yolov3_defect\model_data/yolov3.h5',
"anchors_path": 'D:\Pycharm\object_defect\Yolov3_defect\model_data/yolo_anchors.txt',
"classes_path": 'D:\Pycharm\object_defect\Yolov3_defect\model_data/coco.names',
"score" : 0.3,
"iou" : 0.45,
"model_image_size" : (416, 416),
"gpu_num" : 1,
}
@classmethod
def get_defaults(cls, n):
if n in cls._defaults:
return cls._defaults[n]
else:
return "Unrecognized attribute name '" + n + "'"
def __init__(self, **kwargs):
self.__dict__.update(self._defaults) # set up default values
self.__dict__.update(kwargs) # and update with user overrides
self.class_names = self._get_class()
self.anchors = self._get_anchors()
self.sess = K.get_session()
self.boxes, self.scores, self.classes = self.generate() # 由generate()函数完成目标检测
def _get_class(self):
classes_path = os.path.expanduser(self.classes_path)
with open(classes_path) as f:
class_names = f.readlines()
class_names = [c.strip() for c in class_names]
return class_names
def _get_anchors(self):
anchors_path = os.path.expanduser(self.anchors_path)
with open(anchors_path) as f:
anchors = f.readline()
anchors = [float(x) for x in anchors.split(',')]
# 生成两列的数组
return np.array(anchors).reshape(-1, 2)
def generate(self):
#读取：model路径、anchor box、coco类别，加载模型yolo.h5
model_path = os.path.expanduser(self.model_path)
# endswith() 方法用于判断字符串是否以指定后缀结尾，如果以指定后缀结尾返回True，否则返回False。
# assert（断言）用于判断一个表达式，在表达式条件为 false 的时候触发异常。
assert model_path.endswith('.h5'), 'Keras model or weights must be a .h5 file.'
# Load model, or construct model and load weights.
# anchors 数量
num_anchors = len(self.anchors)
# 类别数量
num_classes = len(self.class_names)
is_tiny_version = num_anchors==6 # default setting
try:
self.yolo_model = load_model(model_path, compile=False)
except:
self.yolo_model = tiny_yolo_body(Input(shape=(None,None,3)), num_anchors//2, num_classes) \
if is_tiny_version else yolo_body(Input(shape=(None,None,3)), num_anchors//3, num_classes)
self.yolo_model.load_weights(self.model_path) # make sure model, anchors and classes match
else:
assert self.yolo_model.layers[-1].output_shape[-1] == \
num_anchors/len(self.yolo_model.output) * (num_classes + 5), \
'Mismatch between model and given anchor and class sizes'
print('{} model, anchors, and classes loaded.'.format(model_path))
# Generate colors for drawing bounding boxes.
# 生成绘图边界框的颜色。
hsv_tuples = [(x / len(self.class_names), 1., 1.)
for x in range(len(self.class_names))]
# colorsys.hsv_to_rgb() 将颜色从HSV坐标转换为RGB坐标。
self.colors = list(map(lambda x: colorsys.hsv_to_rgb(*x), hsv_tuples))
self.colors = list(
map(lambda x: (int(x[0] * 255), int(x[1] * 255), int(x[2] * 255)),
self.colors))
np.random.seed(10101) # 固定seed，可在每次运行中获得一致的颜色
np.random.shuffle(self.colors) # 随机排列颜色以关联相邻的类。
np.random.seed(None) # 将seed重置为默认值。
# Generate output tensor targets for filtered bounding boxes.
# 为过滤后的边界框生成输出张量目标。
self.input_image_shape = K.placeholder(shape=(2, ))
if self.gpu_num>=2:
self.yolo_model = multi_gpu_model(self.yolo_model, gpus=self.gpu_num)
boxes, scores, classes = yolo_eval(self.yolo_model.output, self.anchors,
len(self.class_names), self.input_image_shape,
score_threshold=self.score, iou_threshold=self.iou)
return boxes, scores, classes
def detect_image(self, image):
start = timer()
#调用letterbox_image()函数，即：先生成一个用“绝对灰”R128-G128-B128“填充的416x416新图片，
# 然后用按比例缩放（采样方法：BICUBIC）后的输入图片粘贴，粘贴不到的部分保留为灰色
if self.model_image_size != (None, None):
assert self.model_image_size[0]%32 == 0, 'Multiples of 32 required'
assert self.model_image_size[1]%32 == 0, 'Multiples of 32 required'
boxed_image = letterbox_image(image, tuple(reversed(self.model_image_size)))
# model_image_size定义的宽和高必须是32的整倍数；若没有定义model_image_size，
# 将输入图片的尺寸调整到32的整倍数，并调用letterbox_image()函数进行缩放
else:
new_image_size = (image.width - (image.width % 32),
image.height - (image.height % 32))
boxed_image = letterbox_image(image, new_image_size)
image_data = np.array(boxed_image, dtype='float32')
print(image_data.shape)
image_data /= 255.#将缩放后图片的数值除以255，做归一化
#将（416,416,3）数组调整为（1,416,416,3）元组，满足YOLOv3输入的张量格式
image_data = np.expand_dims(image_data, 0) # Add batch dimension.
out_boxes, out_scores, out_classes = self.sess.run(
[self.boxes, self.scores, self.classes],
feed_dict={#输入参数
self.yolo_model.input: image_data,#输入图片
self.input_image_shape: [image.size[1], image.size[0]], #图片尺寸416x416
K.learning_phase(): 0 #学习模式：0测试/1训练
})
print('Found {} boxes for {}'.format(len(out_boxes), 'img'))
# 设置字体
font = ImageFont.truetype(font='font/FiraMono-Medium.otf',
size=np.floor(3e-2 * image.size[1] + 0.5).astype('int32'))
# 设置目标框线条的宽度
thickness = (image.size[0] + image.size[1]) // 300
#对于c个目标类别中的每个目标框i，调用Pillow画图
for i, c in reversed(list(enumerate(out_classes))):
predicted_class = self.class_names[c] #目标类别的名字
box = out_boxes[i] #目标框
score = out_scores[i] #目标框的置信度评分
label = '{} {:.2f}'.format(predicted_class, score)
draw = ImageDraw.Draw(image) #输出：绘制输入的原始图片
label_size = draw.textsize(label, font) #返回label的宽和高（多少个pixels）.
top, left, bottom, right = box
#目标框的上、左两个坐标小数点后一位四舍五入
top = max(0, np.floor(top + 0.5).astype('int32'))
left = max(0, np.floor(left + 0.5).astype('int32'))
bottom = min(image.size[1], np.floor(bottom + 0.5).astype('int32'))
right = min(image.size[0], np.floor(right + 0.5).astype('int32'))
print(label, (left, top), (right, bottom))
#确定标签（label）起始点位置：左、下
if top - label_size[1] >= 0:
text_origin = np.array([left, top - label_size[1]])
else:
text_origin = np.array([left, top + 1])
# My kingdom for a good redistributable image drawing library.
#画目标框，线条宽度为thickness
for i in range(thickness):
draw.rectangle(
[left + i, top + i, right - i, bottom - i],
outline=self.colors[c])
#画标签框
draw.rectangle(
[tuple(text_origin), tuple(text_origin + label_size)],
fill=self.colors[c])
#填写标签内容
draw.text(text_origin, label, fill=(0, 0, 0), font=font)
del draw
end = timer()
print(end - start)
return image
def close_session(self):
self.sess.close()
def detect_video(yolo, video_path, output_path=""):
import cv2
vid = cv2.VideoCapture(video_path)
if not vid.isOpened():
raise IOError("Couldn't open webcam or video")
video_FourCC = int(vid.get(cv2.CAP_PROP_FOURCC))
video_fps = vid.get(cv2.CAP_PROP_FPS)
video_size = (int(vid.get(cv2.CAP_PROP_FRAME_WIDTH)),
int(vid.get(cv2.CAP_PROP_FRAME_HEIGHT)))
isOutput = True if output_path != "" else False
if isOutput:
print("!!! TYPE:", type(output_path), type(video_FourCC), type(video_fps), type(video_size))
out = cv2.VideoWriter(output_path, video_FourCC, video_fps, video_size)
accum_time = 0
curr_fps = 0
fps = "FPS: ??"
prev_time = timer()
while True:
return_value, frame = vid.read()
image = Image.fromarray(frame)
image = yolo.detect_image(image)
result = np.asarray(image)
curr_time = timer()
exec_time = curr_time - prev_time
prev_time = curr_time
accum_time = accum_time + exec_time
curr_fps = curr_fps + 1
if accum_time > 1:
accum_time = accum_time - 1
fps = "FPS: " + str(curr_fps)
curr_fps = 0
cv2.putText(result, text=fps, org=(3, 15), fontFace=cv2.FONT_HERSHEY_SIMPLEX,
fontScale=0.50, color=(255, 0, 0), thickness=2)
cv2.namedWindow("result", cv2.WINDOW_NORMAL)
cv2.imshow("result", result)
if isOutput:
out.write(result)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
yolo.close_session()
写代码的作者很贴心，分别让我们可以尝试视频和图片的检测，这里他还给了一个读取视频的文件 yolo_video.py 文件，这个文件得在终端运行，别用pycharm直接就运行了，啥也没有。
import sys
import argparse
from yolo import YOLO, detect_video
from PIL import Image
def detect_img(yolo):
while True:
img = input('Input image filename:')
try:
image = Image.open(img)
except:
print('Open Error! Try again!')
continue
else:
r_image = yolo.detect_image(image)
r_image.show()
yolo.close_session()
FLAGS = None
if __name__ == '__main__':
# class YOLO defines the default value, so suppress any default here
parser = argparse.ArgumentParser(argument_default=argparse.SUPPRESS)
'''
Command line options
'''
parser.add_argument(
'--model', type=str,
help='path to model weight file, default ' + YOLO.get_defaults("model_path")
)
parser.add_argument(
'--anchors', type=str,
help='path to anchor definitions, default ' + YOLO.get_defaults("anchors_path")
)
parser.add_argument(
'--classes', type=str,
help='path to class definitions, default ' + YOLO.get_defaults("classes_path")
)
parser.add_argument(
'--gpu_num', type=int,
help='Number of GPU to use, default ' + str(YOLO.get_defaults("gpu_num"))
)
parser.add_argument(
'--image', default=False, action="store_true",
help='Image detection mode, will ignore all positional arguments'
)
'''
Command line positional arguments -- for video detection mode
'''
parser.add_argument(
"--input", nargs='?', type=str,required=False,default='./path2your_video',
help = "Video input path"
)
parser.add_argument(
"--output", nargs='?', type=str, default="",
help = "[Optional] Video output path"
)
FLAGS = parser.parse_args()
if FLAGS.image:
"""
Image detection mode, disregard any remaining command line arguments
"""
print("Image detection mode")
if "input" in FLAGS:
print(" Ignoring remaining command line arguments: " + FLAGS.input + "," + FLAGS.output)
detect_img(YOLO(**vars(FLAGS)))
elif "input" in FLAGS:
detect_video(YOLO(**vars(FLAGS)), FLAGS.input, FLAGS.output)
else:
print("Musath. St specify at least video_input_pee usage with --help.")
为了简单，写了一个简单的代码，直接可以检测图片，就是 test.py 文件，读取模型参数，读取测试文件就可以了
import glob
import os
from PIL import Image
def detect_img(yolo):
path = "D:\VOCdevkit\VOC2007\JPEGImages\*.jpg"
outdir = "D:\VOCdevkit\VOC2007\SegmentationClass"
for jpgfile in glob.glob(path):
img = Image.open(jpgfile)
img = yolo.detect_image(img)
img.save(os.path.join(outdir, os.path.basename(jpgfile)))
yolo.close_session()
最后再来一张结构图，看看大家弄得对不对，当然，我文章里面没说的就是不需要的。
由于上班的原因，没时间改来改去的，再加上笔记本配置不行，就这么地吧，后面的工作交给你们来完善。欢迎留言交流，互相学习
PS： 如果有时间的话，我会考虑在服务器上花钱训练，并且在来一个FasterRCnn版本的进行对比，为了简单，FastRCnn很有可能就在mmdetection上或者Torchvision上进行训练了，这个用起来比较方便。哈哈哈
3052
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
