Image Feature Extraction
Transformers
Safetensors
vehicle_encoder
feature-extraction
vehicle
metric-learning
image-embedding
custom_code
Instructions to use quebeccyb/vehitv-cropped with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use quebeccyb/vehitv-cropped with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="quebeccyb/vehitv-cropped", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("quebeccyb/vehitv-cropped", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
fix: relative import for HF custom-code loading
Browse files
modeling_vehicle_encoder.py
CHANGED
|
@@ -3,7 +3,7 @@ import torch.nn as nn
|
|
| 3 |
import torch.nn.functional as F
|
| 4 |
from transformers import PreTrainedModel
|
| 5 |
|
| 6 |
-
from configuration_vehicle_encoder import VehicleEncoderConfig
|
| 7 |
|
| 8 |
|
| 9 |
class ResBlock(nn.Module):
|
|
|
|
| 3 |
import torch.nn.functional as F
|
| 4 |
from transformers import PreTrainedModel
|
| 5 |
|
| 6 |
+
from .configuration_vehicle_encoder import VehicleEncoderConfig
|
| 7 |
|
| 8 |
|
| 9 |
class ResBlock(nn.Module):
|