End of training

README.md

@@ -0,0 +1,80 @@
+---
+license: other
+base_model: nvidia/mit-b0
+tags:
+- vision
+- image-segmentation
+- generated_from_trainer
+model-index:
+- name: segformer-b0-winter_2
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# segformer-b0-winter_2
+
+This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the johanhag/winter dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0535
+- Mean Iou: 0.3344
+- Mean Accuracy: 0.4082
+- Overall Accuracy: 0.8584
+- Accuracy Unlabeled: nan
+- Accuracy Road: 0.5791
+- Accuracy Side walk: 0.1367
+- Accuracy Car: 0.7716
+- Accuracy Pedestrian: 0.0
+- Accuracy Sign: 0.0
+- Accuracy Other: 0.9616
+- Iou Unlabeled: nan
+- Iou Road: 0.4852
+- Iou Side walk: 0.1124
+- Iou Car: 0.5493
+- Iou Pedestrian: 0.0
+- Iou Sign: 0.0
+- Iou Other: 0.8593
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 6e-05
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Unlabeled | Accuracy Road | Accuracy Side walk | Accuracy Car | Accuracy Pedestrian | Accuracy Sign | Accuracy Other | Iou Unlabeled | Iou Road | Iou Side walk | Iou Car | Iou Pedestrian | Iou Sign | Iou Other |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------------:|:-------------:|:------------------:|:------------:|:-------------------:|:-------------:|:--------------:|:-------------:|:--------:|:-------------:|:-------:|:--------------:|:--------:|:---------:|
+| 1.5205        | 0.37  | 20   | 1.7165          | 0.2199   | 0.4062        | 0.7410           | nan                | 0.6131        | 0.0612             | 0.8217       | 0.0191              | 0.1249        | 0.7972         | 0.0           | 0.4142   | 0.0255        | 0.3422  | 0.0160         | 0.0075   | 0.7342    |
+| 1.206         | 0.74  | 40   | 1.3022          | 0.2637   | 0.3793        | 0.8243           | nan                | 0.6081        | 0.1049             | 0.6391       | 0.0083              | 0.0           | 0.9156         | 0.0           | 0.4387   | 0.0670        | 0.5111  | 0.0083         | 0.0      | 0.8211    |
+| 0.9859        | 1.11  | 60   | 1.1535          | 0.2756   | 0.4094        | 0.8356           | nan                | 0.6077        | 0.2204             | 0.7029       | 0.0                 | 0.0           | 0.9254         | 0.0           | 0.4650   | 0.1159        | 0.5125  | 0.0            | 0.0      | 0.8359    |
+| 0.9968        | 1.48  | 80   | 1.0899          | 0.3171   | 0.3962        | 0.8452           | nan                | 0.5982        | 0.0850             | 0.7523       | 0.0                 | 0.0           | 0.9416         | nan           | 0.4673   | 0.0643        | 0.5239  | 0.0            | 0.0      | 0.8468    |
+| 0.92          | 1.85  | 100  | 1.0535          | 0.3344   | 0.4082        | 0.8584           | nan                | 0.5791        | 0.1367             | 0.7716       | 0.0                 | 0.0           | 0.9616         | nan           | 0.4852   | 0.1124        | 0.5493  | 0.0            | 0.0      | 0.8593    |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,88 @@
+{
+  "_name_or_path": "nvidia/mit-b0",
+  "architectures": [
+    "SegformerForSemanticSegmentation"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout_prob": 0.1,
+  "decoder_hidden_size": 256,
+  "depths": [
+    2,
+    2,
+    2,
+    2
+  ],
+  "downsampling_rates": [
+    1,
+    4,
+    8,
+    16
+  ],
+  "drop_path_rate": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_sizes": [
+    32,
+    64,
+    160,
+    256
+  ],
+  "id2label": {
+    "0": "unlabeled",
+    "1": "road",
+    "2": "side walk",
+    "3": "car",
+    "4": "pedestrian",
+    "5": "sign",
+    "6": "other"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "label2id": {
+    "car": 3,
+    "other": 6,
+    "pedestrian": 4,
+    "road": 1,
+    "side walk": 2,
+    "sign": 5,
+    "unlabeled": 0
+  },
+  "layer_norm_eps": 1e-06,
+  "mlp_ratios": [
+    4,
+    4,
+    4,
+    4
+  ],
+  "model_type": "segformer",
+  "num_attention_heads": [
+    1,
+    2,
+    5,
+    8
+  ],
+  "num_channels": 3,
+  "num_encoder_blocks": 4,
+  "patch_sizes": [
+    7,
+    3,
+    3,
+    3
+  ],
+  "reshape_last_stage": true,
+  "semantic_loss_ignore_index": 255,
+  "sr_ratios": [
+    8,
+    4,
+    2,
+    1
+  ],
+  "strides": [
+    4,
+    2,
+    2,
+    2
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05a5faa7c61425e636a4e151c2a842e8556cbcec35766f9d71d5c6d07becdf09
+size 14889924

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9acacd0b4f9409b5f9e34b8f6fb755bfd13fed64ffd4d48d229a17a68f88e16
+size 4728