Instructions to use merve/openscene-vit-dinov3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use merve/openscene-vit-dinov3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="merve/openscene-vit-dinov3") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoImageProcessor, AutoModelForImageClassification processor = AutoImageProcessor.from_pretrained("merve/openscene-vit-dinov3") model = AutoModelForImageClassification.from_pretrained("merve/openscene-vit-dinov3", device_map="auto") - timm
How to use merve/openscene-vit-dinov3 with timm:
import timm model = timm.create_model("hf_hub:merve/openscene-vit-dinov3", pretrained=True) - Notebooks
- Google Colab
- Kaggle
Training in progress, epoch 1
Browse files- config.json +57 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architecture": "vit_base_patch16_dinov3",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"TimmWrapperForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"do_pooling": true,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
+
"global_pool": "avg",
|
| 9 |
+
"initializer_range": 0.02,
|
| 10 |
+
"label_names": [
|
| 11 |
+
"buildings",
|
| 12 |
+
"forest",
|
| 13 |
+
"glacier",
|
| 14 |
+
"mountain",
|
| 15 |
+
"sea",
|
| 16 |
+
"street"
|
| 17 |
+
],
|
| 18 |
+
"model_args": null,
|
| 19 |
+
"model_type": "timm_wrapper",
|
| 20 |
+
"num_classes": 6,
|
| 21 |
+
"num_features": 768,
|
| 22 |
+
"pretrained_cfg": {
|
| 23 |
+
"classifier": "head",
|
| 24 |
+
"crop_mode": "center",
|
| 25 |
+
"crop_pct": 1.0,
|
| 26 |
+
"custom_load": false,
|
| 27 |
+
"first_conv": "patch_embed.proj",
|
| 28 |
+
"fixed_input_size": false,
|
| 29 |
+
"input_size": [
|
| 30 |
+
3,
|
| 31 |
+
256,
|
| 32 |
+
256
|
| 33 |
+
],
|
| 34 |
+
"interpolation": "bicubic",
|
| 35 |
+
"license": "dinov3",
|
| 36 |
+
"mean": [
|
| 37 |
+
0.485,
|
| 38 |
+
0.456,
|
| 39 |
+
0.406
|
| 40 |
+
],
|
| 41 |
+
"min_input_size": [
|
| 42 |
+
3,
|
| 43 |
+
128,
|
| 44 |
+
128
|
| 45 |
+
],
|
| 46 |
+
"pool_size": null,
|
| 47 |
+
"std": [
|
| 48 |
+
0.229,
|
| 49 |
+
0.224,
|
| 50 |
+
0.225
|
| 51 |
+
],
|
| 52 |
+
"tag": "lvd1689m"
|
| 53 |
+
},
|
| 54 |
+
"problem_type": "single_label_classification",
|
| 55 |
+
"transformers_version": "5.3.0.dev0",
|
| 56 |
+
"use_cache": false
|
| 57 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e49e3ad1f2a52e61ccf3a6825ab64668ca3b8b68916075e29264f9d7806c41a2
|
| 3 |
+
size 342598376
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e80f4a99cc49b720b95b88e24c494ae018d44ead2b8cb8ebde667962ba3bee13
|
| 3 |
+
size 5329
|