Instructions to use spicecloud/spice-cnn-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use spicecloud/spice-cnn-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="spicecloud/spice-cnn-base", 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("spicecloud/spice-cnn-base", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Upload processor
Browse files
image_processing_spice_cnn.py
CHANGED
|
@@ -11,6 +11,7 @@ from transformers.image_transforms import (
|
|
| 11 |
normalize,
|
| 12 |
rescale,
|
| 13 |
resize,
|
|
|
|
| 14 |
to_channel_dimension_format,
|
| 15 |
)
|
| 16 |
from transformers.image_utils import (
|
|
@@ -85,9 +86,6 @@ class SpiceCNNImageProcessor(BaseImageProcessor):
|
|
| 85 |
self.image_std = image_std if image_std is not None else IMAGENET_STANDARD_STD
|
| 86 |
self.padding = padding
|
| 87 |
|
| 88 |
-
def pad(self):
|
| 89 |
-
print("ANODNASODASODNHOI")
|
| 90 |
-
|
| 91 |
def resize(
|
| 92 |
self,
|
| 93 |
image: np.ndarray,
|
|
|
|
| 11 |
normalize,
|
| 12 |
rescale,
|
| 13 |
resize,
|
| 14 |
+
pad,
|
| 15 |
to_channel_dimension_format,
|
| 16 |
)
|
| 17 |
from transformers.image_utils import (
|
|
|
|
| 86 |
self.image_std = image_std if image_std is not None else IMAGENET_STANDARD_STD
|
| 87 |
self.padding = padding
|
| 88 |
|
|
|
|
|
|
|
|
|
|
| 89 |
def resize(
|
| 90 |
self,
|
| 91 |
image: np.ndarray,
|