Wei-Chih

Can confirm this repo works with my 3090: a docker container in linux.

@JordanMakesMaps read it somewhere stating that in newer tensorflow or keras require the return batch as tuple rather than list ``` def __getitem__(self, i): # collect batch data start =...

That's for test time data augmentation. Take a look at the dataloader, some images were flipped, it simply flips it back.

For others' reference. Might have found the reason. The default learning rate might be too large to your custom dataset. Results in making too much of adjustment, and the loss...

> 您好，我也想用自己的数据进行训练，有一点很迷惑，希望您能指教。 > 在数据集导入阶段，她的标签是voc的xml格式，那seam网络输入的标签是一张图片的类别还是有gt的boundbox呢 SEAM only uses classification labels for training. No bounding box labels involved.

> 首先非常感谢您的快速解答，我还想问您一个问题，就是您是怎么进行数据的label标注的，使用labelme吗？生成xml？ If you look into the file in SEAM/voc12/cls_labels.npy, it contains a dictionary of `example.jpg: [0, 1, 0, 1, 0, 0]`. This is what you need as the ground...

> 6. did not need to add them to 20_class_labels.npy, as they were already there I added about 1500 images, extract features extracts all the 12000+ images, but when i...

Let's discuss here so others who have similar issues can refer to this. > I want to include the validation images in training as well. Thats why i dont need...

+1

@dotlineX Would you please elaborate on how to use it with Nextcloud? Thanks