-
Notifications
You must be signed in to change notification settings - Fork 2
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
Batch size #3
Comments
好的,我晚上会检查一下,因为显存占用问题,之前都是用的batch_size=1,没有考虑到>1的情况,不好意思 |
非常感谢光速回复,期待你的分享 |
img_out=utility.GetQuadrupletsImg(inputdata, fake_img, s2img, s2CSMimg)
|
明白了,感谢详尽的解释,受益良多👍 |
感谢分享代码
想请教一下我在尝试调整batch size的时候遇到如下异常,请问您有没有解决方法可以分享?
另外一个问题是调节哪些参数可以有效提升预测的精确度呢?
异常如下, batch_size = 5:
*epoch1:loss_fake:0.13505132
Traceback (most recent call last):
File "train.py", line 133, in
train(myconfig)
File "train.py", line 119, in train
img_out=utility.GetQuadrupletsImg(inputdata, fake_img, s2img, s2CSMimg)
File "/content/drive/My Drive/Colab Notebooks/DSEN2_CR_PYTORCH_fall_200epoch/utils/utils.py", line 175, in GetQuadrupletsImg
img_cld= uint16to8((t.squeeze(img_cld ).cpu().numpy()scale).astype("uint16")).transpose(1,2,0)
ValueError: axes don't match array
The text was updated successfully, but these errors were encountered: