caer.preprocess_from_dir的详细标志错误

Question

我正在跟随OpenCV课程，我正在跟随如何制作一个具有深度学习的辛普森字符检测程序，但是当我尝试创建学习数据时，我得到一个冗长的标志错误。

import os
import caer
import canaro
import numpy as np
import cv2 as cv
import gc
IMG_SIZE = (80,80)
channels = 1
char_path = r'C:/Users/glett/OneDrive/Documents/simpsons_dataset'
char_dict = {}
for char in os.listdir(char_path):
char_dict[char] = len(os.listdir(os.path.join(char_path, char)))
# sort in descending order
char_dict = caer.sort_dict(char_dict, descending=True)
#get top 10 characters
characters = []
count = 0
for i in char_dict:
characters.append(i[0])
count += 1
if count >= 10:
break
#creating training data, grabs character images
train = caer.preprocess_from_dir(char_path, characters, channels=channels, IMG_SIZE=IMG_SIZE, isShuffle=True)

错误:

Traceback (most recent call last):
File "C:UsersglettOneDriveDesktopporgampythonsimpsons_example.py", line 30, in <module>
train = caer.preprocess_from_dir(char_path, characters, channels=channels, IMG_SIZE=IMG_SIZE, isShuffle=True)
File "C:UsersglettAppDataLocalProgramsPythonPython39libsite-packagescaerpreprocess.py", line 64, in preprocess_from_dir
raise ValueError('verbose flag must be either 1 (display progress to terminal) or 0 otherwise')
ValueError: verbose flag must be either 1 (display progress to terminal) or 0 otherwise

Answer 1

如果你想看到你的机器是如何训练模型的，那么在caer.preprocess_from_dir(),verbose = 1中分配verbose的值，如果你不想，那么把verbose = 0。

Answer 2

我觉得少了一行。

characters = []
count = 0
for i in char_dict:
characters.append(i[0])
count += 1
if count >= 10:
break
characters --> you missed this line

你可以试试