Rustam Khadipash

@agniszczotka This worked for me: ``` import torch import torchvision model = torchvision.models.resnet50(pretrained=True, progress=True) torch.save(model.state_dict(), 'checkpoint/resnet50.pth') ``` Replace `resnet50` with `resnet18` if you need so. @DaniellePerri1 Could #107 be the...

@STASYA00 Thanks for finding the problem. While it's correct to comment out random resize and flip, you should always keep image normalization intact (since the model was trained using those...

Can't install on Ubuntu 18.04 and Docker 20.10.8, build 3967b7d: ``` Status: Downloaded newer image for zixia/wechat:3.3.0.115 docker.io/zixia/wechat:3.3.0.115 🚀 Pulling the docker image done. 🚀 Starting DoChat /dɑɑˈtʃæt/ ... +...

Hi! Thanks for your inquiry. The model file is fine, just the procedure of making the program work is a bit complicated. Until now didn't have much time to write...

Now, to run the model need to adjust some parameters. Because tuning depends on several conditions including your hardware (GTA V outlook differs from version to version and hardware), it...

Yes, it is ADEChallengeData2016 dataset, and it needs to be converted first: https://github.com/openseg-group/openseg.pytorch/tree/master/lib/datasets/preprocess/ade20k

Our team has released the SVD training script: https://github.com/mindspore-lab/mindone/tree/master/examples/svd It's still under development, but you can use it for reference.

> What are the GPU requirements for fine tuning @hadipash ? Currently a lot (64 GB), but we're working on reducing VRAM usage.

> @hadipash thats not bad really. You tested it with sharding across multiple GPU's (eg multiple GPU's with

@DataAIPlayer Not sure about LoRA, haven't integrated it yet. However, for vanilla training - yes, need distributed training as a single 64GB GPU can only fit 4 frames.