Zhe Chen
I'm sorry I didn't reproduce this bug for now, maybe I need more information. In addition to mask2former+ViT-Adapter on cityscapes, can you successfully train upernet+ViT-Adapter on ade20k? Such as this...
> I have just downloaded model htc++_beit_adapter_large_fpn_3x_coco.pth and config from this github. But I cannot load model use this command: > > from mmdet.apis import init_detector configFile = 'configs/htc++/htc++_beit_adapter_large_fpn_3x_coco.py' checkpointFile...
Hello, you can check the [documentation](https://mmdetection.readthedocs.io/en/stable/) of mmdet to see if it has this function. Maybe you need to modify the inference code for mmdet.
Hi, using the model trained with stroke perceptual loss can increase the stroke size to a certain extent. But due to the limitation of the effective receptive field, 8192x8192 images...
Yes, URST can be adapted to stroke-controllable-fast-style-transfer. The only problem is that this code is TensorFlow, I don't know how to implement it immediately. I have tried to adapt URST...
> Hi @czczup thanks for your work! You mentioned the following, so have you made any progress on it? > > > I have tried to adapt URST to another...
The pretrained weight seems not to be loaded because I didn't see a warning about the head.weight.
> 用psenet 训练自己的数据集，只要求位置，格式为(x1,y1,x2,y2,x3,y3,x4,y4,"###")，训练的时候loss一直为1，acc为0.  > > 求帮助 文字内容不能标注为###，随便标成什么别的都行
I also reproduced the result of 0.06+, what is the reason for the inconsistency? I use the `zinc.sh` to train the model, and use the same test cmd as dongZheX...
> Note that the ZINC dataset has both the full sets and the subset sets. The current version of our codes corresponds to the full sets. So there is a...