Training error
sacred178953 opened this issue · 6 comments
Dear authors,
I have read about your PASD work,and I used the DIV2K dataset for training,due to the limitation of GPU (48GB of graphics memory), I reduced the epochs, batch size, and steps, but the training progress bar did not move, and in the end, the model weights were saved.
你好，你的数据集可以共享一下吗？作者提供的链接没法访问
你好，你的数据集可以共享一下吗？作者提供的链接没法访问
我数据集在服务器上，没法共享啊
你好，你的数据集可以共享一下吗？作者提供的链接没法访问
直接在浏览器网址复制搜索http://data.vision.ee.ethz.ch/cvl/DIV2K/DIV2K_train_HR.zip ，就可以下载数据集了，但是没有标签文件，所以还是训练不了，我现在就卡在这最后一步
Dear authors, I have read about your PASD work,and I used the DIV2K dataset for training,due to the limitation of GPU (48GB of graphics memory), I reduced the epochs, batch size, and steps, but the training progress bar did not move, and in the end, the model weights were saved.
�It seems like the progress bar did not updated properly.
请问如何生成DIV2K训练集的标签文件呢？
亲爱的作者， 我读过你的PASD工作，我使用DIV2K数据集进行训练，由于GPU的限制（48GB显存），我减少了epochs，batch size，以及steps，但是训练进度条没有动，最后模型权重还是保住了。
你好，请问您最后解决这个问题了吗，我遇到跟您一样的问题