Image Classification
Transformers
Safetensors
nula
computer-vision
cnn
cifar10
adversarial-robustness
stress-test
downsampling
anti-aliasing
custom_code
Instructions to use MamaPearl/nula-cifar10-robust-v0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MamaPearl/nula-cifar10-robust-v0 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="MamaPearl/nula-cifar10-robust-v0", trust_remote_code=True) pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoModelForImageClassification model = AutoModelForImageClassification.from_pretrained("MamaPearl/nula-cifar10-robust-v0", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update preprocessor_config.json
Browse files- preprocessor_config.json +9 -7
preprocessor_config.json
CHANGED
|
@@ -1,13 +1,15 @@
|
|
| 1 |
{
|
| 2 |
-
"do_normalize": true,
|
| 3 |
-
"do_rescale": false,
|
| 4 |
"do_resize": true,
|
| 5 |
-
"image_mean": [0.5, 0.5, 0.5],
|
| 6 |
-
"image_std": [0.5, 0.5, 0.5],
|
| 7 |
-
"image_processor_type": "ViTImageProcessor",
|
| 8 |
-
"resample": 2,
|
| 9 |
"size": {
|
| 10 |
"height": 32,
|
| 11 |
"width": 32
|
| 12 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
}
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
| 2 |
"do_resize": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"size": {
|
| 4 |
"height": 32,
|
| 5 |
"width": 32
|
| 6 |
+
},
|
| 7 |
+
"resample": 3,
|
| 8 |
+
"do_center_crop": false,
|
| 9 |
+
"do_rescale": true,
|
| 10 |
+
"rescale_factor": 0.00392156862745098,
|
| 11 |
+
"do_normalize": true,
|
| 12 |
+
"image_mean": [0.5, 0.5, 0.5],
|
| 13 |
+
"image_std": [0.5, 0.5, 0.5],
|
| 14 |
+
"image_processor_type": "ViTImageProcessor"
|
| 15 |
}
|