您好，请问可以提供您所使用的CASIA-WebFace吗？

[satakiolo]

我使用自己的CASIA-WebFace的准确率只有98%，想试试您的

[wujiyang]

@satakiolo 稍后我会放到百度云

[wujiyang]

@satakiolo
链接：https://pan.baidu.com/s/1eMpfz2jCbZR2XO91hgFnDA
提取码：l2zk

[satakiolo]

太谢谢您了！

[satakiolo]

@satakiolo 链接：https://pan.baidu.com/s/1eMpfz2jCbZR2XO91hgFnDA 提取码：l2zk

@satakiolo 稍后我会放到百度云

作者您好，请问SEResNet50-IR_2只是将SEResNet50-IR再计算了一次？还是有其他意义呢？

[wujiyang]

那个可以忽略

[tiandunx]

厉害厉害

[wujiyang]

@yoyohonyang 自己生成自己训练数据的列表就好了

[xuexingyu24]

@wujiyang Hi could you please share us the .list file along with your CASIA-WebFace dataset ?

[ZZH2950228]

我生成自己数据集的列表txt文件，但是运行train文件出现下面的错误，请问您是怎么解决的 呢？ Traceback (most recent call last): File "train.py", line 255, in train(args) File "train.py", line 59, in train trainset = CASIAWebFace(args.train_root, args.train_file_list, transform=transform) File "/home/zzh/桌面/Face_Pytorch-master/dataset/casia_webface.py", line 42, in init image_path, label_name = info.split(' ') ValueError: not enough values to unpack (expected 2, got 1)

[swuxyj]

@wujiyang Hi could you please share us the .list file along with your CASIA-WebFace dataset ? Maybe you can try try:

import os

with open('webface_align_train.list', 'w') as f:
    root_path = "webface_align_112"
    for index, current_dir in enumerate(os.listdir(root_path)):
        for file in os.listdir(os.path.join(root_path, current_dir)):
            f.write(os.path.join(current_dir, file) + " " + str(index) + "\n")

[jilner]

你好，请问这个是已经对齐的人脸数据集么，谢谢

[Tracy-git]

because you use that generate_data_list.py , has two space （' '） between path and label so you should modify code as: for info in img_label_list: image_path, label_name = info.split(' ') image_list.append(image_path) label_list.append(int(label_name))