Instructions to use mcity-data-engine/fisheye8k_Omnifact_conditional-detr-resnet-101-dc5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mcity-data-engine/fisheye8k_Omnifact_conditional-detr-resnet-101-dc5 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("object-detection", model="mcity-data-engine/fisheye8k_Omnifact_conditional-detr-resnet-101-dc5")# Load model directly from transformers import AutoImageProcessor, AutoModelForObjectDetection processor = AutoImageProcessor.from_pretrained("mcity-data-engine/fisheye8k_Omnifact_conditional-detr-resnet-101-dc5") model = AutoModelForObjectDetection.from_pretrained("mcity-data-engine/fisheye8k_Omnifact_conditional-detr-resnet-101-dc5") - Notebooks
- Google Colab
- Kaggle
Daniel Bogdoll commited on
End of training
Browse files
README.md
CHANGED
|
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [Omnifact/conditional-detr-resnet-101-dc5](https://huggingface.co/Omnifact/conditional-detr-resnet-101-dc5) on the generator dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: 1.
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -50,21 +50,14 @@ The following hyperparameters were used during training:
|
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
|:-------------:|:-----:|:-----:|:---------------:|
|
| 53 |
-
|
|
| 54 |
-
| 0.
|
| 55 |
-
| 0.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.6551 | 9.0 | 47592 | 1.4442 |
|
| 62 |
-
| 0.6407 | 10.0 | 52880 | 1.3509 |
|
| 63 |
-
| 0.6147 | 11.0 | 58168 | 1.4422 |
|
| 64 |
-
| 0.6194 | 12.0 | 63456 | 1.4945 |
|
| 65 |
-
| 0.6086 | 13.0 | 68744 | 1.4436 |
|
| 66 |
-
| 0.587 | 14.0 | 74032 | 1.4244 |
|
| 67 |
-
| 0.5483 | 15.0 | 79320 | 1.4022 |
|
| 68 |
|
| 69 |
|
| 70 |
### Framework versions
|
|
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [Omnifact/conditional-detr-resnet-101-dc5](https://huggingface.co/Omnifact/conditional-detr-resnet-101-dc5) on the generator dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.6175
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
|:-------------:|:-----:|:-----:|:---------------:|
|
| 53 |
+
| 1.0147 | 1.0 | 5288 | 1.5035 |
|
| 54 |
+
| 0.9144 | 2.0 | 10576 | 1.4618 |
|
| 55 |
+
| 0.8685 | 3.0 | 15864 | 1.3823 |
|
| 56 |
+
| 0.8375 | 4.0 | 21152 | 1.5128 |
|
| 57 |
+
| 0.7715 | 5.0 | 26440 | 1.5045 |
|
| 58 |
+
| 0.7664 | 6.0 | 31728 | 1.6914 |
|
| 59 |
+
| 0.7073 | 7.0 | 37016 | 1.6101 |
|
| 60 |
+
| 0.6966 | 8.0 | 42304 | 1.6175 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 61 |
|
| 62 |
|
| 63 |
### Framework versions
|
runs/Feb14_19-40-23_mcity-rtx-4090/events.out.tfevents.1739580024.mcity-rtx-4090.1139582.2
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a17c5fff2cd057457580f7f9ab15b46e687dab20aec74d89c350aad727adf7df
|
| 3 |
+
size 26663
|