-
### System Info
- `transformers` version: 4.36.0.dev0
- Platform: Linux-generic-x86_64
- Python version: 3.8.12
- Huggingface_hub version: 0.19.4
- Safetensors version: 0.4.1
- Accelerate vers…
-
> why the val result and test result from the same epoch are different
test result:
…
-
- [ ] Decide on pipeline setup, network architectures, datasets
- [ ] Neural networks process and run on image data
- [ ] Make a detection library in tensorflow
- [ ] make class to easily…
-
Hello!
thank you for your nice work!
I am currently trying to fine tune GLIP for my custom dataset. I have converted my data to CocoDataset type and set up a config file.
I am able to train th…
-
### System information
- **OS Platform and Distribution (e.g., Linux Ubuntu 16.04)**: Ubuntu 20.04.2 LTS
- **FiftyOne installed from (pip or source)**: pip
- **FiftyOne version (run `fiftyo…
-
Hi folks,
As there are multiple issues here regarding fine-tuning DINOv2 on custom data, questions related to semantic segmentation/depth estimation, image similarity and feature extraction etc. th…
-
Dear author, hello. I have read the instructions on training networks using my own dataset. My dataset includes images and corresponding category annotation JSON files. How can I create my own dataset…
-
**Describe the bug**
The COCODataset implementation uses the COCO API to load in dataset annotations upon initialization. However, since a COCODataset instance is created once for every GPU worker, t…
-
Hi, as I checked the train.py, I cant see the train-dir argument to specify my training directory. Is it possible to train on a custom dataset and would the dataset follow the COCO format
-
env: mmdetection 3.0.0
os :18.04
mmcv:2.0.0
i follow this index https://github.com/open-mmlab/mmdetection/blob/v3.0.0/docs/en/user_guides/semi_det.md
i make cocodataset . run python ./tools/t…