Python tsfresh 自动计算大量的时间序列特征

[https://zhuanlan.zhihu.com/p/99069186](https://zhuanlan.zhihu.com/p/99069186)

LightGBM 决策树 gradient boosting framework

图片文件如果相同，md5是一样的。于是利用此进行图片去重。





```python
import os
import hashlib
def get_md5(file):
    file = open(file, 'rb')
    md5 = hashlib.md5(file.read())
    file.close()
    md5_values = md5.hexdigest()
    return md5_values
file_path =  r"D:\Users\Administrator\Desktop\smokingsig\yolov5k\images"
os.chdir(file_path)
file_list = os.listdir(file_path)
md5_list = []
for file in file_list:
    md5 = get_md5(file)
    if md5 not in md5_list:
        md5_list.append(md5)
    else:
        os.remove(file)
```

相似度  计算量非常大，不太好用：
```python
# -*- encoding=utf-8 -*-
import cv2
import os
class dup_picture:
    def __init__(self):
        self.orb = cv2.ORB_create()
        self.bf = cv2.BFMatcher(cv2.NORM_HAMMING)
    def get_pic_desc(self, img1_path: str):
        img1 = cv2.imread(img1_path, cv2.IMREAD_GRAYSCALE)
        kp1, des1 = self.orb.detectAndCompute(img1, None)
        return des1
    def get_similary(self, des1, des2):
        # knn筛选结果
        matches = self.bf.knnMatch(des1, trainDescriptors=des2, k=2)
        # 查看最大匹配点数目
        good = [m for (m, n) in matches if m.distance < 0.75 * n.distance]
        if len(matches) == 0:
            return 0
        similary = len(good) / len(matches)
        return similary
if __name__ == '__main__':
    duptool = dup_picture()
    file_path = r"D:\PycharmProjects\downloadpicture\all_smoking_picture"
    file_list = os.listdir(file_path)
    file_list = list(filter(lambda x: x.endswith(".jpg"), file_list))  # must .jpg pic
    os.chdir(file_path)
    unique_list = [duptool.get_pic_desc(file_list[0]), ]
    for k,file in enumerate(file_list[1:]):
        print(k)
        des = duptool.get_pic_desc(file)
        if des is None:
            os.remove(file)
            continue
        for des_i in unique_list:
            if duptool.get_similary(des, des_i) > 0.5:
                os.remove(file)
                print(file)
                break
        else:  # Smooth and uninterrupted execution completed
            unique_list.append(des)
```


其余labels处理：

```python
import os
imagespath = r"D:\Users\Administrator\Desktop\smokingsig\yolov5k\images"
labelspath = r"D:\Users\Administrator\Desktop\yololabels"
img_list = os.listdir(imagespath)
lab_list = os.listdir(labelspath)
# ---- read label ----> if none label ----> delete label file
for name in lab_list:
    lfile = os.path.join(labelspath, name)
    if "image" in name:
        with open(lfile, "r") as f:
            res = f.readlines()
        if len(res) == 0:
            os.remove(lfile)
# ---- read label ----> if  label str too short ----> delete label file
for name in lab_list:
    lfile = os.path.join(labelspath, name)
    if "image" in name:
        with open(lfile, "r") as f:
            res = f.readlines()
        if len(res[0]) < 3:
            os.remove(lfile)
# ---- read images names ----> if have not label file ----> delete imgfile
for name in img_list:
    if name[:-4] + ".txt" not in lab_list:
        os.remove(os.path.join(imagespath, name))
```

Python 图片去重 图片文件去重 依据相似度去重 cv2.ORB

# 四种POST 请求方式：





[https://imququ.com/post/four-ways-to-post-data-in-http.html#toc-2](https://imququ.com/post/four-ways-to-post-data-in-http.html#toc-2)

Content-Type: application/x-www-form-urlencoded  最原始表单，参数单一，不能传文件。

Content-Type:multipart/form-data  改进后的表单，能传文件。

Content-Type: application/json  倾向于传json，json规范导致前后端传数据都喜欢用这个，数据生产和消费简单。

# FastAPI 中如何支持

[https://fastapi.tiangolo.com/zh/tutorial/schema-extra-example/](https://fastapi.tiangolo.com/zh/tutorial/schema-extra-example/)

把函数参数改为Body解析即可，而不是FORM解析。

```python
# -*- coding:utf-8 -*-
import traceback
import uvicorn
from typing import Optional
from fastapi import Body, FastAPI
from pydantic import BaseModel
from fastapi.middleware.cors import CORSMiddleware
app = FastAPI(
    title='FastAPI',
    description='FastAPI',
    version='1.0.0',
    docs_url='/docs',
    redoc_url='/redocs',
)
app.add_middleware(
    CORSMiddleware,
    allow_origins=["*"],
    allow_credentials=True,
    allow_methods=["*"],
    allow_headers=["*"],
)
class Item(BaseModel):
    name: str
    description: Optional[str] = None
    price: float
    tax: Optional[float] = None
@app.post("/items/{item_id}")
async def update_item(
        item_id: int,
        item: Item = Body(
            ...,
            example={
                "name": "Foo",
                "description": "A very nice Item",
                "price": 35.4,
                "tax": 3.2,
            },
        ),
):
    results = {"item_id": item_id, "item": item}
    return results
if __name__ == '__main__':
    uvicorn.run('fastapia:app', host='0.0.0.0', port=8001, reload=False, debug=False, workers=1)
```

# PostMan 测试

修改请求头

![在这里插入图片描述](/static/img/images/00319.png)

写raw的原生json字符串

![在这里插入图片描述](/static/img/images/00320.png)


```python
import requests
requests.post(url="http://0.0.0.0:8001/items/1",
              json={
                  "name": "Foo",
                  "description": "A very nice Item",
                  "price": 35.4,
                  "tax": 3.2,
              },
              )
```

FastAPI python content-type: application/json

参考:[https://blog.csdn.net/haveanybody/article/details/86494063](https://blog.csdn.net/haveanybody/article/details/86494063)





# 基础

cv2 打开图片，tensor的shape是（im_height, im_width, channel），BGR格式。**cv2.imread返回的是numpy.ndarray张量。**

pillow 打开图片，RGB格式。Pillow读出来的是PIL.Image.Image对象。

# 打开图片与保存图片

```python
##PIL 读取、保存图片方法
from PIL import Image
img = Image.open("eee.jpg")
img.save("eee_result.jpg")
##cv2 读取、保存图片方法
import cv2
img = cv2.imread("eee.jpg")
cv2.imwrite("eee_result.jpg", img)
##图片文件打开为base64
import base64
def img_base64(img_path):
    with open(img_path, "rb") as f:
        base64_str = base64.b64encode(f.read())
    return base64_str
```

# CV2中的  BGR转RGB

```python
from matplotlib import pyplot as plt
import cv2
img = cv2.imread("eee.jpg")
cv2.imwrite("eee_result.jpg", img)
imgrgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
plt.imshow(imgrgb)
plt.show()
```

# PIL CV2 的相互转换

```python
## PIL转cv2
import cv2
from PIL import Image
import numpy as np
img_rgb = Image.open("eee.jpg")
img_bgr = cv2.cvtColor(np.asarray(img_rgb), cv2.COLOR_RGB2BGR) # 成为cv2的numpy.ndarray
```

```python
## PIL转cv2
import cv2
from PIL import Image
img_bgr = cv2.imread("eee.jpg")
img_rgb = Image.fromarray(cv2.cvtColor(img_bgr, cv2.COLOR_BGR2RGB)) # 成为Pillow的PIL.Image.Image对象
```


# PIL base64 的相互转换

```python
##PIL转base64
import base64
from io import BytesIO
from PIL import Image
def pillow_to_base64(image):
    img_buffer = BytesIO()
    image.save(img_buffer, format='JPEG')
    byte_data = img_buffer.getvalue()
    base64_str = base64.b64encode(byte_data)
    return base64_str
# example
img = Image.open("eee.jpg")
print(pillow_to_base64(img))
```

```python
##PIL转base64
import base64
from io import BytesIO
from PIL import Image
def base64_to_pillow(base64_str):
    image = base64.b64decode(base64_str)
    image = BytesIO(image)
    image = Image.open(image)
    return image
# example
with open("eee.jpg", "rb") as f:
    base64_str = base64.b64encode(f.read())
print(base64_to_pillow(base64_str))
```

# CV2 base64 的相互转换

```python
# cv2 转 base64
import base64
import cv2
def cv2_to_base64(image):
    base64_str = cv2.imencode('.jpg', image)[1].tostring()
    base64_str = base64.b64encode(base64_str)
    return base64_str
# example
image = cv2.imread("eee.jpg")
print(cv2_to_base64(image))
```

```python
# base64 转 cv2
import base64
import numpy as np
import cv2
from PIL import Image
from io import BytesIO
def base64_to_cv2(base64_str):
    imgString = base64.b64decode(base64_str)
    nparr = np.frombuffer(imgString, np.uint8)
    image = cv2.imdecode(nparr, cv2.IMREAD_COLOR)
    return image
# example
with open("eee.jpg", "rb") as f:
    base64_str = base64.b64encode(f.read())
print(base64_to_cv2(base64_str))
```


# FastAPI中bytes 转CV2

```python
img = cv2.imdecode(np.frombuffer(file, dtype=np.uint8), cv2.IMREAD_COLOR)
```

# FastAPI中uploadfile  转CV2

```python
img = cv2.imdecode(np.fromstring(fileb.file.read(), np.uint8), cv2.IMREAD_COLOR)
```


# CV2 numpy  转成 字节流（open("file.jpg",'rb')）

参考：[https://blog.csdn.net/sinat_29957455/article/details/107208432](https://blog.csdn.net/sinat_29957455/article/details/107208432)

```python
img = cv2.imread("lpr1.png")
# 对数组的图片格式进行编码
success, encoded_image = cv2.imencode(".jpg", img)
# 将数组转为bytes
f = encoded_image.tobytes()
```