enesmsahin

Hi, I am trying to reproduce your results for NoCaps challenge. For the VinVL + VIVO model (NoCaps challenge) which object labels (tags) did you use for VIVO pretraining and...

Hi, In VinVL paper, you mention following: > By adding VIVO [9] pre-training, our VinVL improves the original VIVO result by 6 CIDEr points and creates a new SoTA. As...

Release of an Inpainting Model

1

Hi, Thank you for your work, it is very good. Is it possible that you train/share a ControlNet model trained for inpainting (conditioned on a binary mask)? Current SD inpainting...

Error while loading "Selective (CSL) TResNet-L" model

3

Runtime Error occurs while loading state_dict for provided TResNet-L model. I think provided pretrained model and **TResnetL** class differ. **Selective (CSL) - TResNet-M** works without any problems. # Console Output...

* Modified image destination path since current path requires root access to call `os.makedirs("/results")`. * Returned `tensor_batch` from `inference(im, model, class_list, args)` function since it is to be used in...

save_state() fails when using DeepSpeed with multiple models where some models are frozen some are being trained

2

### System Info ```Shell - `Accelerate` version: 0.35.0.dev0 - Platform: Linux-5.10.0-32-cloud-amd64-x86_64-with-glibc2.31 - `accelerate` bash location: /opt/conda/envs/flux_cn_exp/bin/accelerate - Python version: 3.10.10 - Numpy version: 1.26.4 - PyTorch version (GPU?): 2.3.0+cu121 (True)...