|
# Fine-tuning Details |
|
"nielsr/dinov2-base" # pre-trained model from which to fine-tune |
|
|
|
"Graphcore/vit-base-ipu" # config specific to the IPU (Used POD4) |
|
|
|
Using: [https://github.com/graphcore/Gradient-HuggingFace/tree/main/image-classification](https://github.com/graphcore/Gradient-HuggingFace/commit/826b72cba150be52e7420a3440a31e3096b73c78) |
|
|
|
Poplar SDK: v3.2.1 |
|
|
|
Dataset: |
|
|
|
load a custom dataset from local/remote files or folders using the ImageFolder feature |
|
option 1: local/remote files (supporting the following formats: tar, gzip, zip, xz, rar, zstd) |
|
url = "https://madm.dfki.de/files/sentinel/EuroSAT.zip" |
|
files = list(Path(dataset_dir).rglob("EuroSAT.zip")) |
|
|