Commit
·
f72c7d7
1
Parent(s):
f63cd8e
Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# To fine-tuning Details
|
2 |
+
"facebook/dino-vitb16" # pre-trained model from which to fine-tune
|
3 |
+
|
4 |
+
"Graphcore/vit-base-ipu" # config specific to the IPU (Used POD4)
|
5 |
+
|
6 |
+
Using: [https://github.com/graphcore/Gradient-HuggingFace/tree/main/image-classification](https://github.com/graphcore/Gradient-HuggingFace/commit/826b72cba150be52e7420a3440a31e3096b73c78)
|
7 |
+
|
8 |
+
Run the notebooks in this repository:
|
9 |
+
[](https://ipu.dev/3YOs4Js)
|
10 |
+
|
11 |
+
|
12 |
+
Poplar SDK: v3.2.1
|
13 |
+
|
14 |
+
Dataset:
|
15 |
+
|
16 |
+
load a custom dataset from local/remote files or folders using the ImageFolder feature
|
17 |
+
option 1: local/remote files (supporting the following formats: tar, gzip, zip, xz, rar, zstd)
|
18 |
+
url = "https://madm.dfki.de/files/sentinel/EuroSAT.zip"
|
19 |
+
files = list(Path(dataset_dir).rglob("EuroSAT.zip"))
|
20 |
+
|
21 |
+
[](https://www.graphcore.ai/join-community)
|