造车先做三蹦子220101--机器学习字符(字母、和数字识别)的“小白鼠”与“果蝇”-编程知识

“0”数字字符零的图片(16*16点阵)：

#Letter23Digital23R231006d.pyimport torch
import torch.nn as nn
import torch.optim as optim   #optimizer = optim.SGD(model.parameters(), lr=0.01)
from PIL import Image
from PIL import ImageDraw
from PIL import ImageFont
#from PIL import ImageDraw, ImageFontfrom torchvision import transforms
import matplotlib.pyplot as plt   #matplotlib显示字符(结果)Times500=4590# 参数设置
font_path = "arial.ttf"    #"e:\\22Letter23r1002\\arial.ttf"    #e:\\arial.ttf"
#siz28e28 = 28
siz28e14=32
#characters = ["2","4","我"] +[str(i) for i in range(8,9)] + ["A","Z"]   #["A", "B"]
Characts01 = ["8","-","+","X","2"] +[str(i) for i in range(0,2)] print(Characts01)# 1. 生成字符和数字的点阵数据
def render_char(char, siz28e14):image = Image.new("L", (siz28e14, siz28e14), "white")draw = ImageDraw.Draw(image)font = ImageFont.truetype(font_path, siz28e14)
#-----------------------------------------w03 = draw.textlength(char, font=font)h03 = siz28e14print("{[w3",w03, "h3",w03 ,"]} ")
#-----------------------------------------draw.text(((siz28e14-w03)/2, (siz28e14-h03)/2), char, font=font, fill="black")return imageData01 = []
labels = []
for i, char in enumerate(Characts01):img = render_char(char, siz28e14)Data01.append(transforms.ToTensor()(img))labels.append(i)print("i",i,char)#-----------------------------
# 2. 显示取得的 arial.ttf 字体的图像
for i in range(len(Data01)):plt.imshow(Data01[i].squeeze().cpu().numpy(), cmap="gray")plt.title("char:"+Characts01[i])plt.axis("off")
#  plt.show()#-----------------------------# 2. 训练神经网络模型
class SimpleNet(nn.Module):def __init__(self, num_classes):super(SimpleNet, self).__init__()self.fc = nn.Linear(siz28e14 * siz28e14, num_classes)def forward(self, x):x = x.view(-1, siz28e14 * siz28e14)x = self.fc(x)return xmodel = SimpleNet(len(Characts01))
loss_function = nn.CrossEntropyLoss()
#optimizer = optim.SGD(model.parameters(), lr=0.01)
optimizer = optim.SGD(model.parameters(), lr=0.003)for epoch in range(Times500):#8000):#1000):inputs = torch.stack(Data01)targets = torch.tensor(labels)optimizer.zero_grad()outputs = model(inputs)loss = loss_function(outputs, targets)loss.backward()optimizer.step()# 3. 使用模型进行预测
def predict_image(img_path):model.eval()img = Image.open(img_path).convert("L").resize((siz28e14, siz28e14))img_tensor = transforms.ToTensor()(img).unsqueeze(0)output = model(img_tensor)_, predicted = output.max(1)return Characts01[predicted[0]]#01//8_"8"----
im="f8_16x18.png"
predicted_char = predict_image(im)
print(f"预测的字符为: {predicted_char}")plt.imshow(Image.open(im))
plt.title(f"Predicted: {predicted_char}")
plt.show()#1//1-minus"1"----
im="_1_16x16.png"
predicted_char = predict_image(im)
print(f"预测的字符为: {predicted_char}")plt.imshow(Image.open(im))
plt.title(f"Predicted: {predicted_char}")
plt.show()#2//我-"我"----
im="wo19x19.png"
predicted_char = predict_image(im)
print(f"预测的字符为: {predicted_char}")plt.imshow(Image.open(im))
plt.title(f"Predicted: {predicted_char}")
plt.show()#3//8-"8"----
im="8_16x16.png"
predicted_char = predict_image(im)
print(f"预测的字符为: {predicted_char}")# 使用matplotlib显示结果
plt.imshow(Image.open(im))
plt.title(f"Predicted: {predicted_char}")
#plt.axis("off")
plt.show()#4//minus-minus"-"----
im="f:\\22Letter23r1002\minus16x16.png"
predicted_char = predict_image(im)
print(f"预测的字符为: {predicted_char}")plt.imshow(Image.open(im))
plt.title(f"Predicted: {predicted_char}")
plt.show()

造车先做三蹦子的原理是:

torch,tensorflew,pytorch这个相当于马达、发动机、变速器等底层原件……

一、造车要不要先研究马达、轮子、发动机？
当然！必须！

二、

研究完元器件马达、轮子、发动机就该造……
就可以造宝马？奔驰？Prius、本田、混动了吗？

没那么简单……

对于初级架构师傅来讲……

学习 Prius的新型架构当然有用！

但是，能完整的架构出来一辆五菱宏光、架构出一辆老头乐，架构出一辆三蹦子……那才是一位合格的架构师

如果一个伪装的架构师问你：

我需要三年时间、三个亿$金钱架构出一辆特斯了、Prius混动汽车…… 给钱吧！？

你应该这样回复他：

那我只给你三个月时间，只给你10万~100万人民币…… 请你先给俺架构出一辆老头乐的或五菱宏光！！

做好了，

咱们开展下个任务！！

做不好，那您不叫架构师…… 骗子称号更适合您！

同样道理，一个合格的外科医生，

在给患者病人做手术以前，当然应该是先解剖过小白鼠、和青蛙；

我读过 Caffe的完整代码，这相当于解剖尸体；

重新遭过轮子。

这次，就手工撸一个文字（字符）识别的框架出来…… 作为机器学习的“三蹦子”、小白鼠、或者“果蝇”

下面Demo就是字符(数字、字母)识别的基本框架……

先用 torch完成……

import torch
import torch.nn as nn
import torch.optim as optim
from PIL import Image, ImageDraw, ImageFont
from torchvision import transforms
import matplotlib.pyplot as plt# 参数设置
font_path = "e:\\arial.ttf"
siz28e28 = 28
characters = [str(i) for i in range(0, 10)] + ["A", "B"]# 1. 生成字符和数字的点阵数据
def render_char(char, siz28e28):image = Image.new("L", (siz28e28, siz28e28), "white")draw = ImageDraw.Draw(image)font = ImageFont.truetype(font_path, siz28e28)
#----------------------------------------------------------
#    w, h = draw.textsize(char, font=font)# 使用textbox方法来获取文本的边界框
#    left, upper, right, lower = draw.textbbox((0, 0), char, font=font)
#    w01, h01 = right - left, lower - upper
#    print("[right",right," _left",left, " _lower",lower, " _upper",upper ,")")
#    print("(w1",w01, "h1",h01 ,"] ")
#    w02, h02 = draw.textsize(char, font=font)    //draw.textsize()函数新版本DeprecationWarning: textsize is deprecated and will be removed in Pillow 10 (2023-07-01). Use textbbox or textlength instead.
#    print("{[w2",w02, "h2",w02 ,"]} ")w03 = draw.textlength(char, font=font)h03 = siz28e28print("{[w3",w03, "h3",w03 ,"]} ")
#=============================================draw.text(((siz28e28-w03)/2, (siz28e28-h03)/2), char, font=font, fill="black")return imagedata = []
labels = []
for i, char in enumerate(characters):img = render_char(char, siz28e28)data.append(transforms.ToTensor()(img))labels.append(i)# 2. 训练神经网络模型
class SimpleNet(nn.Module):def __init__(self, num_classes):super(SimpleNet, self).__init__()self.fc = nn.Linear(siz28e28 * siz28e28, num_classes)def forward(self, x):x = x.view(-1, siz28e28 * siz28e28)x = self.fc(x)return xmodel = SimpleNet(len(characters))
loss_function = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01)for epoch in range(1000):inputs = torch.stack(data)targets = torch.tensor(labels)optimizer.zero_grad()outputs = model(inputs)loss = loss_function(outputs, targets)loss.backward()optimizer.step()# 3. 使用模型进行预测
def predict_image(img_path):model.eval()img = Image.open(img_path).convert("L").resize((siz28e28, siz28e28))img_tensor = transforms.ToTensor()(img).unsqueeze(0)output = model(img_tensor)_, predicted = output.max(1)return characters[predicted[0]]# 预测E盘的图像
#img_path = "E:\\i.png"
img_path = "E:\\256A256.png"
predicted_char = predict_image(img_path)
print(f"预测的字符为: {predicted_char}")# 使用matplotlib显示结果
plt.imshow(Image.open(img_path))
plt.title(f"Predicted: {predicted_char}")
plt.axis("off")
plt.show()