Instructions to use HichTala/DiffusionDet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use HichTala/DiffusionDet with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("object-detection", model="HichTala/DiffusionDet", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("HichTala/DiffusionDet", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Update image_processing_diffusiondet.py
Browse files
image_processing_diffusiondet.py
CHANGED
|
@@ -200,18 +200,10 @@ def get_numpy_to_framework_fn(arr) -> Callable:
|
|
| 200 |
"""
|
| 201 |
if isinstance(arr, np.ndarray):
|
| 202 |
return np.array
|
| 203 |
-
if is_tf_available() and is_tf_tensor(arr):
|
| 204 |
-
import tensorflow as tf
|
| 205 |
-
|
| 206 |
-
return tf.convert_to_tensor
|
| 207 |
if is_torch_available() and is_torch_tensor(arr):
|
| 208 |
import torch
|
| 209 |
|
| 210 |
return torch.tensor
|
| 211 |
-
if is_flax_available() and is_jax_tensor(arr):
|
| 212 |
-
import jax.numpy as jnp
|
| 213 |
-
|
| 214 |
-
return jnp.array
|
| 215 |
raise ValueError(f"Cannot convert arrays of type {type(arr)}")
|
| 216 |
|
| 217 |
|
|
|
|
| 200 |
"""
|
| 201 |
if isinstance(arr, np.ndarray):
|
| 202 |
return np.array
|
|
|
|
|
|
|
|
|
|
|
|
|
| 203 |
if is_torch_available() and is_torch_tensor(arr):
|
| 204 |
import torch
|
| 205 |
|
| 206 |
return torch.tensor
|
|
|
|
|
|
|
|
|
|
|
|
|
| 207 |
raise ValueError(f"Cannot convert arrays of type {type(arr)}")
|
| 208 |
|
| 209 |
|