代码拉取完成,页面将自动刷新
import cv2
from matplotlib import pyplot as plt
import os
import numpy as np
import torch.nn as nn
import torch
import os
import json
from PIL import Image
from torchvision import transforms
import pandas as pd
def image_split(image):
# 图像去噪灰度处理
def gray_guss(image):
image = cv2.GaussianBlur(image, (3, 3), 0)
gray_image = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)
return gray_image
#车牌字符分割
gray_image = gray_guss(image)
# 图像阈值化操作——获得二值化图
ret, image = cv2.threshold(gray_image, 0, 255, cv2.THRESH_OTSU)
#plt_show(image)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3, 3))
image = cv2.dilate(image, kernel)
img_thre = image
# 查找轮廓
contours, hierarchy = cv2.findContours(image, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
words = []
word_images = []
#对所有轮廓逐一操作
for item in contours:
word = []
rect = cv2.boundingRect(item)
x = rect[0]
y = rect[1]
weight = rect[2]
height = rect[3]
word.append(x)
word.append(y)
word.append(weight)
word.append(height)
words.append(word)
# 排序,车牌号有顺序。words是一个嵌套列表
words = sorted(words,key=lambda s:s[0],reverse=False)
i = 0
#word中存放轮廓的起始点和宽高
for word in words:
# 筛选字符的轮廓
if (word[3] > (word[2] * 2)) and (word[3] < (word[2] * 3.5)) and (word[2] > 25):
i = i+1
splite_image = image[word[1]:word[1] + word[3], word[0]:word[0] + word[2]]
word_images.append(splite_image)
return word_images
class BasicBlock(nn.Module):
expansion = 1
def __init__(self, in_channel, out_channel, stride=1, downsample=None, **kwargs):
super(BasicBlock, self).__init__()
self.conv1 = nn.Conv2d(in_channels=in_channel, out_channels=out_channel,
kernel_size=3, stride=stride, padding=1, bias=False)
self.bn1 = nn.BatchNorm2d(out_channel)
self.relu = nn.ReLU()
self.conv2 = nn.Conv2d(in_channels=out_channel, out_channels=out_channel,
kernel_size=3, stride=1, padding=1, bias=False)
self.bn2 = nn.BatchNorm2d(out_channel)
self.downsample = downsample
def forward(self, x):
identity = x
if self.downsample is not None:
identity = self.downsample(x)
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
out += identity
out = self.relu(out)
return out
class ResNet(nn.Module):
def __init__(self,
block,
blocks_num,
num_classes=1000,
include_top=True,
groups=1,
width_per_group=64):
super(ResNet, self).__init__()
self.include_top = include_top
self.in_channel = 64
self.groups = groups
self.width_per_group = width_per_group
self.conv1 = nn.Conv2d(3, self.in_channel, kernel_size=7, stride=2,
padding=3, bias=False)
self.bn1 = nn.BatchNorm2d(self.in_channel)
self.relu = nn.ReLU(inplace=True)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.layer1 = self._make_layer(block, 64, blocks_num[0])
self.layer2 = self._make_layer(block, 128, blocks_num[1], stride=2)
self.layer3 = self._make_layer(block, 256, blocks_num[2], stride=2)
self.layer4 = self._make_layer(block, 512, blocks_num[3], stride=2)
if self.include_top:
self.avgpool = nn.AdaptiveAvgPool2d((1, 1)) # output size = (1, 1)
self.fc = nn.Linear(512 * block.expansion, num_classes)
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
def _make_layer(self, block, channel, block_num, stride=1):
downsample = None
if stride != 1 or self.in_channel != channel * block.expansion:
downsample = nn.Sequential(
nn.Conv2d(self.in_channel, channel * block.expansion, kernel_size=1, stride=stride, bias=False),
nn.BatchNorm2d(channel * block.expansion))
layers = []
layers.append(block(self.in_channel,
channel,
downsample=downsample,
stride=stride,
groups=self.groups,
width_per_group=self.width_per_group))
self.in_channel = channel * block.expansion
for _ in range(1, block_num):
layers.append(block(self.in_channel,
channel,
groups=self.groups,
width_per_group=self.width_per_group))
return nn.Sequential(*layers)
def forward(self, x):
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
x = self.maxpool(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
if self.include_top:
x = self.avgpool(x)
x = torch.flatten(x, 1)
x = self.fc(x)
return x
def resnet18(num_classes=1000, include_top=True):
return ResNet(BasicBlock, [2, 2, 2, 2], num_classes=num_classes, include_top=include_top)
str_resu = ''
def main(word_images):
global str_resu,print_res
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
data_transform = transforms.Compose([
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])])
# load image
for i in range(len(word_images)):
# img = Image.open(img_path)
# plt.imshow(img)
img = word_images[i]
img = Image.fromarray(img).convert('RGB')
img = img.resize((20, 20))
# [N, C, H, W]
img = data_transform(img)
# expand batch dimension
img = torch.unsqueeze(img, dim=0)
# read class_indict
json_path = './class_indices.json'
assert os.path.exists(json_path), "file: '{}' dose not exist.".format(json_path)
json_file = open(json_path, "r")
class_indict = json.load(json_file)
# create model
model = resnet18(num_classes=65).to(device)
# load model weights
weights_path = "./resNet18-111.pth"
assert os.path.exists(weights_path), "file: '{}' dose not exist.".format(weights_path)
model.load_state_dict(torch.load(weights_path, map_location=device))
# prediction
model.eval()
with torch.no_grad():
# predict class
output = torch.squeeze(model(img.to(device))).cpu()
predict = torch.softmax(output, dim=0)
predict_cla = torch.argmax(predict).numpy()
# print(predict_cla)
print_res = "str: {} predict: {:.3}".format(class_indict[str(predict_cla)],predict[predict_cla].numpy())
print(print_res)
str_resu += class_indict[str(predict_cla)]
return str_resu
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。