e96031413

# 無重複數字
# input: name_list = [0, 1, 2, 3, 8]
for idx, num in enumerate(set(name_list)):
  if idx != num:
    name_list[idx] = idx
# output: name_list = [0, 1, 2, 3, 4]

# 有重複數字
# input: name_list = [0, 2, 2, 1, 6, 6]
for idx, num in enumerate(set(name_list)):

e96031413

# evaluate the clustering performance
from sklearn.cluster import KMeans
from sklearn.metrics.cluster import normalized_mutual_info_score
import numpy as np

def evaluation(X, Y):
    classN = np.max(Y)+1
    kmeans = KMeans(n_clusters=classN).fit(X)
    nmi = normalized_mutual_info_score(Y, kmeans.labels_, average_method='arithmetic')
    return nmi

e96031413

# https://stackoverflow.com/questions/63761717/load-image-dataset
# https://stackoverflow.com/questions/60655280/how-to-split-an-image-dataset-in-x-train-y-train-x-test-y-test-by-tensorflow

import tensorflow as tf
import pandas as pd

train_df = pd.read_csv('train.csv')
train_df['class'] = train_df['class'].apply(str)

train_datagen = tf.keras.preprocessing.image.ImageDataGenerator(horizontal_flip=True, vertical_flip=True,)

e96031413

import numpy as np
from sklearn import metrics
from sklearn.metrics import roc_auc_score
y = np.array([1, 1, 2, 2])
#scores可以是模型預測結果(Label)
#scores也可以是模型預測的confidence(softmax probability)
scores = np.array([1, 1, 2, 2])
scores = np.array([0.1, 0.4, 0.35, 0.8])
area_under_curve = roc_auc_score(y, scores)

e96031413

 def eval(loader, gt_labels_t, output_file="output.txt"):
    G.eval()  # 特徵提取器
    F1.eval() # 分類器
    size = 0
    correct = 0
    
    y_pred=[]
    y_true=[]
    pred_prob = None
    pred_result = None

e96031413

import torch.nn.functional as F
import torch
import numpy as np
from torch.autograd import Function
import torch.nn as nn
from pdb import set_trace as breakpoint
import sys
import math
from torch.nn.parameter import Parameter
from torch.nn import init

e96031413

# LabelSmoothing.py

# https://www.aiuai.cn/aifarm1333.html 示例 3
# From: Github - NVIDIA/DeepLearningExamples/PyTorch/Classification
# smoothing.py
import torch
import torch.nn as nn

# 一般版本LabelSmoothing
class LabelSmoothing(nn.Module):

e96031413

# https://stackoverflow.com/a/45925049/13369757
import matplotlib.pyplot as plt 
import numpy as np

fig, host = plt.subplots(figsize=(12,10)) # (width, height) in inches
    
par1 = host.twinx()
par2 = host.twinx()

host.set_xlabel("Threshold")

e96031413

import numpy as np
import torch
import pickle
from torch.utils.data import Dataset, DataLoader

# 提取特徵
def extract(loader):
    featureExtractor.eval()
    features = None
    with torch.no_grad():

e96031413

import os
import shutil

fileListingFile = "missclassified_file_path.txt"
outputDir = "./"

# sample path in txt: /root/notebooks/XXXXX/datasets/XXXXXXXX.jpg

with open(fileListingFile, "r") as file:
    fileNames = [file.strip() for file in file.readlines()]