Instructions to use Vrjb/SegFormer_b2_10 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Vrjb/SegFormer_b2_10 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoImageProcessor, SegformerForSemanticSegmentation processor = AutoImageProcessor.from_pretrained("Vrjb/SegFormer_b2_10") model = SegformerForSemanticSegmentation.from_pretrained("Vrjb/SegFormer_b2_10", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Model save
Browse files- README.md +45 -45
- model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -16,53 +16,53 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [nvidia/segformer-b2-finetuned-cityscapes-1024-1024](https://huggingface.co/nvidia/segformer-b2-finetuned-cityscapes-1024-1024) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- eval_loss: 0.
|
| 20 |
-
- eval_mean_iou: 0.
|
| 21 |
-
- eval_mean_accuracy: 0.
|
| 22 |
-
- eval_overall_accuracy: 0.
|
| 23 |
-
- eval_accuracy_road: 0.
|
| 24 |
-
- eval_accuracy_sidewalk: 0.
|
| 25 |
-
- eval_accuracy_building: 0.
|
| 26 |
-
- eval_accuracy_wall: 0.
|
| 27 |
-
- eval_accuracy_fence: 0.
|
| 28 |
-
- eval_accuracy_pole: 0.
|
| 29 |
-
- eval_accuracy_traffic light: 0.
|
| 30 |
-
- eval_accuracy_traffic sign: 0.
|
| 31 |
-
- eval_accuracy_vegetation: 0.
|
| 32 |
-
- eval_accuracy_terrain: 0.
|
| 33 |
-
- eval_accuracy_sky: 0.
|
| 34 |
- eval_accuracy_person: 0.9096
|
| 35 |
-
- eval_accuracy_rider: 0.
|
| 36 |
-
- eval_accuracy_car: 0.
|
| 37 |
-
- eval_accuracy_truck: 0.
|
| 38 |
-
- eval_accuracy_bus: 0.
|
| 39 |
-
- eval_accuracy_train: 0.
|
| 40 |
-
- eval_accuracy_motorcycle: 0.
|
| 41 |
-
- eval_accuracy_bicycle: 0.
|
| 42 |
- eval_iou_road: 0.9845
|
| 43 |
-
- eval_iou_sidewalk: 0.
|
| 44 |
-
- eval_iou_building: 0.
|
| 45 |
-
- eval_iou_wall: 0.
|
| 46 |
-
- eval_iou_fence: 0.
|
| 47 |
-
- eval_iou_pole: 0.
|
| 48 |
-
- eval_iou_traffic light: 0.
|
| 49 |
-
- eval_iou_traffic sign: 0.
|
| 50 |
-
- eval_iou_vegetation: 0.
|
| 51 |
-
- eval_iou_terrain: 0.
|
| 52 |
-
- eval_iou_sky: 0.
|
| 53 |
-
- eval_iou_person: 0.
|
| 54 |
-
- eval_iou_rider: 0.
|
| 55 |
-
- eval_iou_car: 0.
|
| 56 |
-
- eval_iou_truck: 0.
|
| 57 |
-
- eval_iou_bus: 0.
|
| 58 |
-
- eval_iou_train: 0.
|
| 59 |
-
- eval_iou_motorcycle: 0.
|
| 60 |
-
- eval_iou_bicycle: 0.
|
| 61 |
-
- eval_runtime:
|
| 62 |
-
- eval_samples_per_second: 2.
|
| 63 |
-
- eval_steps_per_second: 0.
|
| 64 |
-
- epoch:
|
| 65 |
-
- step:
|
| 66 |
|
| 67 |
## Model description
|
| 68 |
|
|
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [nvidia/segformer-b2-finetuned-cityscapes-1024-1024](https://huggingface.co/nvidia/segformer-b2-finetuned-cityscapes-1024-1024) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- eval_loss: 0.8160
|
| 20 |
+
- eval_mean_iou: 0.7793
|
| 21 |
+
- eval_mean_accuracy: 0.8652
|
| 22 |
+
- eval_overall_accuracy: 0.9612
|
| 23 |
+
- eval_accuracy_road: 0.9908
|
| 24 |
+
- eval_accuracy_sidewalk: 0.9352
|
| 25 |
+
- eval_accuracy_building: 0.9621
|
| 26 |
+
- eval_accuracy_wall: 0.6658
|
| 27 |
+
- eval_accuracy_fence: 0.6972
|
| 28 |
+
- eval_accuracy_pole: 0.7413
|
| 29 |
+
- eval_accuracy_traffic light: 0.8709
|
| 30 |
+
- eval_accuracy_traffic sign: 0.8898
|
| 31 |
+
- eval_accuracy_vegetation: 0.9636
|
| 32 |
+
- eval_accuracy_terrain: 0.7521
|
| 33 |
+
- eval_accuracy_sky: 0.9818
|
| 34 |
- eval_accuracy_person: 0.9096
|
| 35 |
+
- eval_accuracy_rider: 0.7726
|
| 36 |
+
- eval_accuracy_car: 0.9789
|
| 37 |
+
- eval_accuracy_truck: 0.8699
|
| 38 |
+
- eval_accuracy_bus: 0.9473
|
| 39 |
+
- eval_accuracy_train: 0.8303
|
| 40 |
+
- eval_accuracy_motorcycle: 0.7929
|
| 41 |
+
- eval_accuracy_bicycle: 0.8875
|
| 42 |
- eval_iou_road: 0.9845
|
| 43 |
+
- eval_iou_sidewalk: 0.8693
|
| 44 |
+
- eval_iou_building: 0.9236
|
| 45 |
+
- eval_iou_wall: 0.6059
|
| 46 |
+
- eval_iou_fence: 0.5920
|
| 47 |
+
- eval_iou_pole: 0.5962
|
| 48 |
+
- eval_iou_traffic light: 0.6853
|
| 49 |
+
- eval_iou_traffic sign: 0.7853
|
| 50 |
+
- eval_iou_vegetation: 0.9248
|
| 51 |
+
- eval_iou_terrain: 0.6660
|
| 52 |
+
- eval_iou_sky: 0.9486
|
| 53 |
+
- eval_iou_person: 0.7982
|
| 54 |
+
- eval_iou_rider: 0.5994
|
| 55 |
+
- eval_iou_car: 0.9496
|
| 56 |
+
- eval_iou_truck: 0.8225
|
| 57 |
+
- eval_iou_bus: 0.8680
|
| 58 |
+
- eval_iou_train: 0.7867
|
| 59 |
+
- eval_iou_motorcycle: 0.6412
|
| 60 |
+
- eval_iou_bicycle: 0.7603
|
| 61 |
+
- eval_runtime: 202.0304
|
| 62 |
+
- eval_samples_per_second: 2.475
|
| 63 |
+
- eval_steps_per_second: 0.619
|
| 64 |
+
- epoch: 53.7634
|
| 65 |
+
- step: 10000
|
| 66 |
|
| 67 |
## Model description
|
| 68 |
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 109496316
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81ce68bbcde1cfcea87a204cbc79a7b4989ceea844c73662b88f677c81da479c
|
| 3 |
size 109496316
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5368
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ced65c221ccfd5c8f3c8473a0cf3651ba4d36ea2c0af961ea2404ab88e7018e3
|
| 3 |
size 5368
|