-
Traceback (most recent call last):
File "test.py", line 319, in
test(opt.data,
File "test.py", line 90, in test
dataloader = create_dataloader(data[task], imgsz, batch_size, gs, opt, …
-
Great work! I wonder when will the custom demo online.
-
Hi, I want to train this for a custom dataset for my research purpose? Can you tell me which scripts I need to run for training a scratch model after modifying dataloader?
tfc-0 updated
5 months ago
-
- [x] Implement custom dataloader for YOLOv8
- [x] create a baseline / reference from vanilla yolov8
- [ ] Data augmentation
- [x] Incorporate other countries in training
- [ ] Freeze layers befo…
-
### System Info
- `transformers` version: 4.37.2
- Platform: macOS-14.5-arm64-arm-64bit
- Python version: 3.11.9
- Huggingface_hub version: 0.23.1
- Safetensors version: 0.4.2
- Accelerate ver…
-
Hi,
I have a datafetcher where I use 2 dataloaders in sequence: the first to translate from 1 ID to another, the second to fetch data corresponding to the second ID.
`loader1.load(id1).thenCompo…
-
My question on SO has zero answers but describes the problem the best I think:
https://stackoverflow.com/questions/73650751/get-list-of-fields-to-resolve-from-a-graphql-resolver-supporting-include-d…
-
A new method of loading the data by batch was developed and applied to the Colab notebook. This method caused the original error to signal loss calculation to blow up, so the loss function was change…
-
**Is your feature request related to a problem? Please describe.**
It is not currently straightforward to pass external dataloaders to train a model. In particular, loading `torch.Tensor` data and di…
j-bac updated
3 months ago
-
Hi team,
I am trying to train/fine-tune swin_5scale model on a custom dataset which has 7 classes to train on. below is the script to start the training. I am using one of the uploaded 5scale_swin …