读取所有图片
"""
文件结构
train
├── 0
| ├── 1.png
| ├── 2.png
| └── 3.png
└── 1
├── 4.png
├── 5.png
└── 6.png
...
"""
train_jpg = glob.glob('./train/*/*')
"""
['./train//0/1.png'
'./train//0/2.png'
'./train//0/3.png' ...
'./train//1/4.png'
'./train//1/5.png'
'./train//1/6.png']
"""
图片尺寸分析
from pathlib import Path
from PIL import Image
import numpy as np
import matplotlib.pyplot as plt
p = Path("./data/GHIM-20/")
img_list = p.glob("[0-9]*/*.jpg")
w_h = []
channel = []
for img in img_list:
arr = np.array(Image.open(str(img)))
shape = arr.shape
w_h.append(list(shape[:-1]))
channel.append(shape[-1])
print("channel", set(channel))
w_h = np.array(w_h)
plt.scatter(w_h[:,0], w_h[:,1])
plt.show()