更新接口

This commit is contained in:
Viajero 2025-09-15 19:43:47 +08:00
parent a688e17e4e
commit 233ef20ce2
8 changed files with 44 additions and 4 deletions

View File

Before

Width:  |  Height:  |  Size: 3.8 KiB

After

Width:  |  Height:  |  Size: 3.8 KiB

View File

Before

Width:  |  Height:  |  Size: 3.0 KiB

After

Width:  |  Height:  |  Size: 3.0 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 4.0 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 7.3 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 64 KiB

View File

@ -1,3 +1,4 @@
# 导入必要的库
import torch
import torch.nn as nn
import cv2
@ -11,6 +12,7 @@ from PIL import Image
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
# LPRNet字符集定义与训练时保持一致
# 包含中国省份简称、数字、字母和特殊字符
CHARS = ['', '', '', '', '', '', '', '', '', '',
'', '', '', '', '', '', '', '', '', '',
'', '', '', '', '', '', '', '', '', '', '',
@ -19,84 +21,115 @@ CHARS = ['京', '沪', '津', '渝', '冀', '晋', '蒙', '辽', '吉', '黑',
'L', 'M', 'N', 'P', 'Q', 'R', 'S', 'T', 'U', 'V',
'W', 'X', 'Y', 'Z', 'I', 'O', '-']
# 创建字符到索引的映射字典
CHARS_DICT = {char: i for i, char in enumerate(CHARS)}
# 简化的LPRNet模型定义
# 简化的LPRNet模型定义 - 基础卷积块
class small_basic_block(nn.Module):
def __init__(self, ch_in, ch_out):
super(small_basic_block, self).__init__()
# 定义一个小的基本卷积块,包含四个卷积层
self.block = nn.Sequential(
# 1x1卷积降低通道数
nn.Conv2d(ch_in, ch_out // 4, kernel_size=1),
nn.ReLU(),
# 3x1卷积处理水平特征
nn.Conv2d(ch_out // 4, ch_out // 4, kernel_size=(3, 1), padding=(1, 0)),
nn.ReLU(),
# 1x3卷积处理垂直特征
nn.Conv2d(ch_out // 4, ch_out // 4, kernel_size=(1, 3), padding=(0, 1)),
nn.ReLU(),
# 1x1卷积恢复通道数
nn.Conv2d(ch_out // 4, ch_out, kernel_size=1),
)
def forward(self, x):
return self.block(x)
# LPRNet模型定义 - 车牌识别网络
class LPRNet(nn.Module):
def __init__(self, lpr_max_len, phase, class_num, dropout_rate):
super(LPRNet, self).__init__()
self.phase = phase
self.lpr_max_len = lpr_max_len
self.class_num = class_num
# 定义主干网络
self.backbone = nn.Sequential(
# 初始卷积层
nn.Conv2d(in_channels=3, out_channels=64, kernel_size=3, stride=1), # 0
nn.BatchNorm2d(num_features=64),
nn.ReLU(), # 2
# 最大池化层
nn.MaxPool3d(kernel_size=(1, 3, 3), stride=(1, 1, 1)),
# 第一个基本块
small_basic_block(ch_in=64, ch_out=128), # *** 4 ***
nn.BatchNorm2d(num_features=128),
nn.ReLU(), # 6
# 第二个池化层
nn.MaxPool3d(kernel_size=(1, 3, 3), stride=(2, 1, 2)),
# 第二个基本块
small_basic_block(ch_in=64, ch_out=256), # 8
nn.BatchNorm2d(num_features=256),
nn.ReLU(), # 10
# 第三个基本块
small_basic_block(ch_in=256, ch_out=256), # *** 11 ***
nn.BatchNorm2d(num_features=256),
nn.ReLU(), # 13
# 第三个池化层
nn.MaxPool3d(kernel_size=(1, 3, 3), stride=(4, 1, 2)), # 14
# Dropout层防止过拟合
nn.Dropout(dropout_rate),
# 特征提取卷积层
nn.Conv2d(in_channels=64, out_channels=256, kernel_size=(1, 4), stride=1), # 16
nn.BatchNorm2d(num_features=256),
nn.ReLU(), # 18
# 第二个Dropout层
nn.Dropout(dropout_rate),
# 分类卷积层
nn.Conv2d(in_channels=256, out_channels=class_num, kernel_size=(13, 1), stride=1), # 20
nn.BatchNorm2d(num_features=class_num),
nn.ReLU(), # 22
)
# 定义容器层,用于融合全局上下文信息
self.container = nn.Sequential(
nn.Conv2d(in_channels=448+self.class_num, out_channels=self.class_num, kernel_size=(1,1), stride=(1,1)),
)
def forward(self, x):
# 保存中间特征
keep_features = list()
for i, layer in enumerate(self.backbone.children()):
x = layer(x)
# 保存特定层的输出特征
if i in [2, 6, 13, 22]: # [2, 4, 8, 11, 22]
keep_features.append(x)
# 处理全局上下文信息
global_context = list()
for i, f in enumerate(keep_features):
# 对不同层的特征进行不同尺度的平均池化
if i in [0, 1]:
f = nn.AvgPool2d(kernel_size=5, stride=5)(f)
if i in [2]:
f = nn.AvgPool2d(kernel_size=(4, 10), stride=(4, 2))(f)
# 对特征进行归一化处理
f_pow = torch.pow(f, 2)
f_mean = torch.mean(f_pow)
f = torch.div(f, f_mean)
global_context.append(f)
# 拼接全局上下文特征
x = torch.cat(global_context, 1)
# 通过容器层处理
x = self.container(x)
# 对序列维度进行平均,得到最终输出
logits = torch.mean(x, dim=2)
return logits
# LPRNet推理类
class LPRNetInference:
def __init__(self, model_path=None, img_size=[94, 24], lpr_max_len=8, dropout_rate=0.5):
"""
@ -109,6 +142,7 @@ class LPRNetInference:
"""
self.img_size = img_size
self.lpr_max_len = lpr_max_len
# 检测是否有可用的CUDA设备
self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
# 设置默认模型路径
@ -130,6 +164,7 @@ class LPRNetInference:
else:
print(f"Warning: 模型文件不存在或未指定: {model_path}. 使用随机权重.")
# 将模型移动到指定设备并设置为评估模式
self.model.to(self.device)
self.model.eval()
@ -164,9 +199,11 @@ class LPRNetInference:
image_array = cv2.resize(image_array, tuple(self.img_size))
# 使用与训练时相同的预处理方式
# 归一化处理减去127.5并乘以0.0078125,将像素值从[0,255]映射到[-1,1]
image_array = image_array.astype('float32')
image_array -= 127.5
image_array *= 0.0078125
# 调整维度顺序从HWC到CHW
image_array = np.transpose(image_array, (2, 0, 1)) # HWC -> CHW
# 转换为tensor并添加batch维度
@ -186,7 +223,7 @@ class LPRNetInference:
prebs = logits.cpu().detach().numpy()
preb = prebs[0, :, :] # 取第一个batch [num_classes, sequence_length]
# 贪婪解码:对每个时间步选择最大概率的字符
# 贪婪解码: 对每个时间步选择最大概率的字符
preb_label = []
for j in range(preb.shape[1]): # 遍历每个时间步
preb_label.append(np.argmax(preb[:, j], axis=0))
@ -248,7 +285,7 @@ class LPRNetInference:
print(f"预测图像失败: {e}")
return None, 0.0
# 全局变量
# 全局变量,用于存储模型实例
lpr_model = None
def LPRNinitialize_model():
@ -295,6 +332,9 @@ def LPRNmodel_predict(image_array):
return ['', '', '', '0', '0', '0', '0', '0']
try:
# 使用OpenCV调整图像大小到模型要求的尺寸
image_array = cv2.resize(image_array, (128, 48))
print(f"666999图片尺寸: {image_array.shape}")
# 预测车牌号
predicted_text, confidence = lpr_model.predict(image_array)

View File

@ -11,7 +11,6 @@ from yolopart.detector import LicensePlateYOLO
#选择使用哪个模块
# from LPRNET_part.lpr_interface import LPRNmodel_predict
# from LPRNET_part.lpr_interface import LPRNinitialize_model
#使用OCR
# from OCR_part.ocr_interface import LPRNmodel_predict
# from OCR_part.ocr_interface import LPRNinitialize_model

View File

@ -85,6 +85,7 @@ def test_image_loading():
# 方法2: 支持中文路径的方式
try:
img2 = cv2.imdecode(np.fromfile(image_path, dtype=np.uint8), cv2.IMREAD_COLOR)
# img2 = cv2.resize(img2,(128,48))
print(f"cv2.imdecode结果: {img2 is not None}")
if img2 is not None:
print(f"图片尺寸: {img2.shape}")