-
Notifications
You must be signed in to change notification settings - Fork 3
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
准确率只有50%,无法达到预期结果;数据处理方法是用于CIFAR10的而不是LandUse #3
Comments
@DumnBird 已收到您的 issue,今天我会去再看一下代码,稍晚些给您回复,先提供 checkpoint |
@DumnBird 我在 LeNet 代码的后面备注了 如果把图像 resize 成 64x64,该如何处理,您可以参考一下。 |
我数据导入改成 transforms_test = transforms.Compose([ |
@DumnBird 收到,恭喜。期待您的 repo |
您好,我改过网络后在test集上依然只有接近70的准确率,您能否提供一下您修改过后的版本,谢谢 |
您好,我下载了代码,调了两天参,发现准确率大概在50---60%之间。
然后我查看了代码,数据处理这里:
`transforms_train = transforms.Compose([
transforms.RandomCrop(32, padding=4),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))
])
transforms_test = transforms.Compose([
transforms.RandomCrop(32, padding=4),
transforms.ToTensor(),
transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))
])`
这个显然是CIFAR10的处理方式,而LandUse的大小是256而不是32,均值和标准差与CIFAR10也不同。
作者能否查看下,是不是传错了代码?
或者可否给一份checkpoint及LandUse的代码?
感谢!
The text was updated successfully, but these errors were encountered: