-
Hi Nils, quick question, what is the best way to train with MNRL? For one query can I have a list of positive passages? Or should only have one passage? And can a query have many positive passages?
…
-
# Editor note: There is a known workaround further down on this issue, which is to NOT use Python lists, but instead using something else, e.g., torch.tensor directly. See https://github.com/pytorch/p…
-
Hello,
I am about to add my own custom data set in a fork of the project. Since this data is still unreleased, and I never created a PyTorch Dataloader for it, I am not bound to a given dataset st…
-
Hello,
I'm using WebVid10M dataset, and passing the following decoder args:
```
decoder_kwargs = {
"n_frames": 16, # get 16 frames from each video
"fps": 8,
"num_threads": 12, # …
-
So I have a dataset comprising of 1900 images in total and having 55 classes. I am experimenting with RTMDet tiny, medium and large models. But when I start training it shows ETA as 4 days for 700 epo…
-
### 🐛 Describe the bug
If the `params` in one `param_groups` cannot be divided into `world_size` parts, an error will be raised here:
https://github.com/hpcaitech/ColossalAI/blob/57a6d7685cf05b076…
-
Hello @IrohXu ,
Is this repo supports to train the network on custom dataset? If not so, do you have any idea what parameters should change while training on custom dataset? What I should keep in my …
-
Hi all,
Thanks for the great work to provide more suitable primitives for Machine Learning in Heliophysics!
It would be great to have a Pytorch [DataLoader](https://pytorch.org/tutorials/beginn…
-
Thank you for great work.
Could you tell me which dataset I should prepare when I use nuScenes dataset??
Now, I'd like to try to run the evaluation script with nuScenes dataset.
I followed the …
-
Many thanks to BoxInst authors for sharing the codebase for training and evaluating using BoxInst.
I am facing an issue while finetuning BoxInst models on my custom data.
`Specs: Multi-gpu training …