Jan Zdenek
Jan Zdenek
Hello! I would like to ask about the discriminators used for training of the model. The repository includes only inference time code and the discriminators aren't included so I wanted...
Hi! I've been trying to reproduce the results in your paper on IAM dataset by generating new data with the code in this repository, and using the model for text...
Hi, I have a question about the ground truth files for FSNS curriculum learning. I've created the ground truth file with images containing up to 2 words using this command:...
Hi! I'd like to ask about pretrained models for Places365. In Readme, it says that Places365 pretrained models are coming soon. Is there still a plan to make them available...
Hello, can I ask you a question? Why [the input of conv1 in SpatialTransformer](https://github.com/aicaffeinelife/Pytorch-STN/blob/master/models/STNModule.py#L49) should be detached? Look forward to your reply. _Originally posted by @wuwenbin970731 in https://github.com/aicaffeinelife/Pytorch-STN/issues/5#issuecomment-659167815_
Hi! I think that conv4 should be called on https://github.com/aicaffeinelife/Pytorch-STN/blob/master/models/STNModule.py#L54 instead of conv3. You call conv3 before that already? Am I right? I can send a PR if you want.
The KOSMOS-G paper and the project page mention using LoRA for image generation with KOSMOS-G. How and in what format can we add trained LoRAs to the base SD model...
Are the default settings of parameters such as learning rate the parameters that you used for training? I cannot train the network for more than about 10 epochs as the...
Could you please upload the ImageNet pretrained VGG weights also somewhere else than on Baidu?
I am trying to understand what is the usage difference between these two scripts. If I understand correctly, then both are used to compute latents and store them to disk...