End of training

README.md

@@ -1,7 +1,7 @@
 ---
-base_model: nvidia/mit-b0
 library_name: transformers
 license: other
+base_model: nvidia/mit-b0
 tags:
 - vision
 - image-segmentation
@@ -16,16 +16,28 @@ should probably proofread and complete it, then remove this comment. -->
 
 # segformer-b0-finetuned-segments-satellite-terrain
 
-This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the ZeeeWP/terrain_map_obstacle dataset.
+This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the ZeeeWP/terrain_map dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4376
-- Mean Iou: 0.3519
-- Mean Accuracy: 0.7038
-- Overall Accuracy: 0.7038
+- Loss: 1.5864
+- Mean Iou: 0.2321
+- Mean Accuracy: 0.3696
+- Overall Accuracy: 0.5634
 - Accuracy Unlabeled: nan
-- Accuracy Obstacle: 0.7038
+- Accuracy Sand: 0.7791
+- Accuracy Cliff: 0.7374
+- Accuracy Bedrock flat: 0.6510
+- Accuracy Bedrock lowhill: 0.0354
+- Accuracy Bedrock highhill: 0.0
+- Accuracy Gravel low hill: 0.3842
+- Accuracy Gravel high hill: 0.0
 - Iou Unlabeled: 0.0
-- Iou Obstacle: 0.7038
+- Iou Sand: 0.6893
+- Iou Cliff: 0.4361
+- Iou Bedrock flat: 0.4508
+- Iou Bedrock lowhill: 0.0337
+- Iou Bedrock highhill: 0.0
+- Iou Gravel low hill: 0.2469
+- Iou Gravel high hill: 0.0
 
 ## Model description
 
@@ -54,11 +66,12 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Unlabeled | Accuracy Obstacle | Iou Unlabeled | Iou Obstacle |
-|:-------------:|:------:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------------:|:-----------------:|:-------------:|:------------:|
-| 0.4655        | 3.3333 | 20   | 0.5979          | 0.2393   | 0.4786        | 0.4786           | nan                | 0.4786            | 0.0           | 0.4786       |
-| 0.409         | 6.6667 | 40   | 0.5183          | 0.3392   | 0.6784        | 0.6784           | nan                | 0.6784            | 0.0           | 0.6784       |
-| 0.3966        | 10.0   | 60   | 0.4376          | 0.3519   | 0.7038        | 0.7038           | nan                | 0.7038            | 0.0           | 0.7038       |
+| Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Unlabeled | Accuracy Sand | Accuracy Cliff | Accuracy Bedrock flat | Accuracy Bedrock lowhill | Accuracy Bedrock highhill | Accuracy Gravel low hill | Accuracy Gravel high hill | Iou Unlabeled | Iou Sand | Iou Cliff | Iou Bedrock flat | Iou Bedrock lowhill | Iou Bedrock highhill | Iou Gravel low hill | Iou Gravel high hill |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------------:|:-------------:|:--------------:|:---------------------:|:------------------------:|:-------------------------:|:------------------------:|:-------------------------:|:-------------:|:--------:|:---------:|:----------------:|:-------------------:|:--------------------:|:-------------------:|:--------------------:|
+| 1.8112        | 2.5   | 20   | 1.9952          | 0.1801   | 0.3131        | 0.4952           | nan                | 0.5584        | 0.8000         | 0.5986                | 0.0492                   | 0.0055                    | 0.1607                   | 0.0192                    | 0.0           | 0.4056   | 0.4166    | 0.4358           | 0.0456              | 0.0018               | 0.1338              | 0.0019               |
+| 1.6328        | 5.0   | 40   | 1.7866          | 0.2145   | 0.3514        | 0.5421           | nan                | 0.7209        | 0.8280         | 0.6081                | 0.0391                   | 0.0                       | 0.2636                   | 0.0                       | 0.0           | 0.6272   | 0.4126    | 0.4458           | 0.0376              | 0.0                  | 0.1931              | 0.0                  |
+| 1.5004        | 7.5   | 60   | 1.6383          | 0.2316   | 0.3695        | 0.5571           | nan                | 0.7734        | 0.7044         | 0.6298                | 0.0443                   | 0.0                       | 0.4344                   | 0.0                       | 0.0           | 0.6825   | 0.4346    | 0.4371           | 0.0411              | 0.0                  | 0.2576              | 0.0                  |
+| 1.5562        | 10.0  | 80   | 1.5864          | 0.2321   | 0.3696        | 0.5634           | nan                | 0.7791        | 0.7374         | 0.6510                | 0.0354                   | 0.0                       | 0.3842                   | 0.0                       | 0.0           | 0.6893   | 0.4361    | 0.4508           | 0.0337              | 0.0                  | 0.2469              | 0.0                  |
 
 
 ### Framework versions

config.json

@@ -29,12 +29,24 @@
   ],
   "id2label": {
     "0": "unlabeled",
-    "1": "obstacle"
+    "1": "sand",
+    "2": "cliff",
+    "3": "bedrock flat",
+    "4": "bedrock lowhill",
+    "5": "bedrock highhill",
+    "6": "gravel low hill",
+    "7": "gravel high hill"
   },
   "image_size": 224,
   "initializer_range": 0.02,
   "label2id": {
-    "obstacle": 1,
+    "bedrock flat": 3,
+    "bedrock highhill": 5,
+    "bedrock lowhill": 4,
+    "cliff": 2,
+    "gravel high hill": 7,
+    "gravel low hill": 6,
+    "sand": 1,
     "unlabeled": 0
   },
   "layer_norm_eps": 1e-06,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b608baf6d0b0eb5096e3e316b320adc3ec67b35752d6a1c96cc37b579403d361
-size 14884776
+oid sha256:616e4e4284794b8ee5b86b54b87e68e15f8497a1c8e456819a0f22f5e2785580
+size 14890952

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddbb945fca2a22375825417feedc73f2a6864ba792b88882465d477b485a03a7
+oid sha256:7e091ee813ad71c2b1f3bcd8846db964aa8127fa321d5f3ce0237741d3fae47b
 size 5240