Model save

README.md

@@ -0,0 +1,110 @@
+---
+library_name: transformers
+license: other
+base_model: nvidia/segformer-b2-finetuned-cityscapes-1024-1024
+tags:
+- generated_from_trainer
+model-index:
+- name: SegFormer_b2_10
+  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_b2_10
+
+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.
+It achieves the following results on the evaluation set:
+- Loss: 0.5167
+- Mean Iou: 0.7247
+- Mean Accuracy: 0.8591
+- Overall Accuracy: 0.9529
+- Accuracy Road: 0.9898
+- Accuracy Sidewalk: 0.9111
+- Accuracy Building: 0.9463
+- Accuracy Wall: 0.7661
+- Accuracy Fence: 0.6741
+- Accuracy Pole: 0.7748
+- Accuracy Traffic light: 0.8544
+- Accuracy Traffic sign: 0.8774
+- Accuracy Vegetation: 0.9441
+- Accuracy Terrain: 0.8160
+- Accuracy Sky: 0.9784
+- Accuracy Person: 0.8991
+- Accuracy Rider: 0.6656
+- Accuracy Car: 0.9748
+- Accuracy Truck: 0.8970
+- Accuracy Bus: 0.9630
+- Accuracy Train: 0.7704
+- Accuracy Motorcycle: 0.8112
+- Accuracy Bicycle: 0.8096
+- Iou Road: 0.9813
+- Iou Sidewalk: 0.8484
+- Iou Building: 0.9108
+- Iou Wall: 0.5660
+- Iou Fence: 0.5429
+- Iou Pole: 0.5432
+- Iou Traffic light: 0.6432
+- Iou Traffic sign: 0.7370
+- Iou Vegetation: 0.9145
+- Iou Terrain: 0.6393
+- Iou Sky: 0.9408
+- Iou Person: 0.7631
+- Iou Rider: 0.5321
+- Iou Car: 0.9365
+- Iou Truck: 0.6980
+- Iou Bus: 0.7964
+- Iou Train: 0.6506
+- Iou Motorcycle: 0.4226
+- Iou Bicycle: 0.7024
+
+## 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: 0.0003
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 100
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Road | Accuracy Sidewalk | Accuracy Building | Accuracy Wall | Accuracy Fence | Accuracy Pole | Accuracy Traffic light | Accuracy Traffic sign | Accuracy Vegetation | Accuracy Terrain | Accuracy Sky | Accuracy Person | Accuracy Rider | Accuracy Car | Accuracy Truck | Accuracy Bus | Accuracy Train | Accuracy Motorcycle | Accuracy Bicycle | Iou Road | Iou Sidewalk | Iou Building | Iou Wall | Iou Fence | Iou Pole | Iou Traffic light | Iou Traffic sign | Iou Vegetation | Iou Terrain | Iou Sky | Iou Person | Iou Rider | Iou Car | Iou Truck | Iou Bus | Iou Train | Iou Motorcycle | Iou Bicycle |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:-------------:|:-----------------:|:-----------------:|:-------------:|:--------------:|:-------------:|:----------------------:|:---------------------:|:-------------------:|:----------------:|:------------:|:---------------:|:--------------:|:------------:|:--------------:|:------------:|:--------------:|:-------------------:|:----------------:|:--------:|:------------:|:------------:|:--------:|:---------:|:--------:|:-----------------:|:----------------:|:--------------:|:-----------:|:-------:|:----------:|:---------:|:-------:|:---------:|:-------:|:---------:|:--------------:|:-----------:|
+| 0.6256        | 0.5376 | 100  | 0.5263          | 0.7506   | 0.8621        | 0.9557           | 0.9876        | 0.9318            | 0.9534            | 0.6814        | 0.6843         | 0.7548        | 0.8823                 | 0.8804                | 0.9512              | 0.7907           | 0.9853       | 0.9179          | 0.7311         | 0.9728       | 0.7997         | 0.9236       | 0.8712         | 0.7905              | 0.8894           | 0.9818   | 0.8545       | 0.9154       | 0.5961   | 0.5660    | 0.5567   | 0.6367            | 0.7428           | 0.9184         | 0.6327      | 0.9388  | 0.7618     | 0.5505    | 0.9430  | 0.7080    | 0.8237  | 0.8082    | 0.5890         | 0.7369      |
+| 0.59          | 1.0753 | 200  | 0.5212          | 0.7550   | 0.8708        | 0.9556           | 0.9864        | 0.9236            | 0.9500            | 0.7202        | 0.7442         | 0.7704        | 0.8940                 | 0.8695                | 0.9544              | 0.7913           | 0.9788       | 0.8917          | 0.7595         | 0.9737       | 0.8668         | 0.9480       | 0.8541         | 0.7533              | 0.9161           | 0.9813   | 0.8531       | 0.9158       | 0.6249   | 0.5892    | 0.5508   | 0.6286            | 0.7511           | 0.9175         | 0.6390      | 0.9429  | 0.7688     | 0.5530    | 0.9395  | 0.7695    | 0.8346  | 0.7812    | 0.5917         | 0.7122      |
+| 0.5591        | 1.6129 | 300  | 0.5206          | 0.7576   | 0.8623        | 0.9560           | 0.9876        | 0.9318            | 0.9528            | 0.7480        | 0.7113         | 0.7688        | 0.8691                 | 0.8717                | 0.9490              | 0.7434           | 0.9854       | 0.9115          | 0.6649         | 0.9765       | 0.8764         | 0.9409       | 0.8491         | 0.7446              | 0.9010           | 0.9818   | 0.8523       | 0.9171       | 0.6258   | 0.5625    | 0.5498   | 0.6449            | 0.7538           | 0.9169         | 0.6314      | 0.9420  | 0.7642     | 0.5360    | 0.9431  | 0.7962    | 0.8561  | 0.7758    | 0.6099         | 0.7342      |
+| 0.5347        | 2.1505 | 400  | 0.5164          | 0.7430   | 0.8682        | 0.9555           | 0.9887        | 0.9261            | 0.9505            | 0.7457        | 0.7474         | 0.7617        | 0.8961                 | 0.8824                | 0.9465              | 0.8092           | 0.9845       | 0.9055          | 0.7155         | 0.9699       | 0.9010         | 0.9649       | 0.7364         | 0.7812              | 0.8822           | 0.9820   | 0.8559       | 0.9150       | 0.6156   | 0.5943    | 0.5575   | 0.6146            | 0.7583           | 0.9167         | 0.6338      | 0.9421  | 0.7646     | 0.5371    | 0.9409  | 0.7665    | 0.7978  | 0.6930    | 0.5012         | 0.7308      |
+| 0.5261        | 2.6882 | 500  | 0.5176          | 0.7407   | 0.8634        | 0.9556           | 0.9877        | 0.9316            | 0.9513            | 0.6787        | 0.6770         | 0.7510        | 0.8908                 | 0.8933                | 0.9544              | 0.7683           | 0.9865       | 0.9013          | 0.6974         | 0.9761       | 0.8451         | 0.9410       | 0.8679         | 0.8479              | 0.8567           | 0.9822   | 0.8570       | 0.9151       | 0.5789   | 0.5500    | 0.5622   | 0.6288            | 0.7493           | 0.9180         | 0.6435      | 0.9412  | 0.7667     | 0.5364    | 0.9407  | 0.7605    | 0.8396  | 0.7786    | 0.4161         | 0.7091      |
+| 0.5826        | 3.2258 | 600  | 0.5166          | 0.7471   | 0.8750        | 0.9546           | 0.9856        | 0.9343            | 0.9494            | 0.7320        | 0.6651         | 0.7644        | 0.8907                 | 0.9116                | 0.9511              | 0.8201           | 0.9753       | 0.8815          | 0.7652         | 0.9710       | 0.8999         | 0.9477       | 0.9025         | 0.7898              | 0.8882           | 0.9807   | 0.8491       | 0.9137       | 0.6172   | 0.5483    | 0.5496   | 0.6166            | 0.7341           | 0.9164         | 0.6601      | 0.9415  | 0.7570     | 0.5231    | 0.9413  | 0.7407    | 0.8306  | 0.7864    | 0.5471         | 0.7409      |
+| 0.5139        | 3.7634 | 700  | 0.5175          | 0.7480   | 0.8636        | 0.9547           | 0.9830        | 0.9441            | 0.9517            | 0.8080        | 0.6542         | 0.7597        | 0.8686                 | 0.8828                | 0.9565              | 0.7031           | 0.9824       | 0.8762          | 0.7318         | 0.9701       | 0.9060         | 0.9467       | 0.8122         | 0.7864              | 0.8852           | 0.9786   | 0.8376       | 0.9156       | 0.6239   | 0.5640    | 0.5548   | 0.6565            | 0.7502           | 0.9194         | 0.6256      | 0.9399  | 0.7696     | 0.5146    | 0.9393  | 0.7800    | 0.8430  | 0.7744    | 0.4908         | 0.7347      |
+| 0.5545        | 4.3011 | 800  | 0.5167          | 0.7247   | 0.8591        | 0.9529           | 0.9898        | 0.9111            | 0.9463            | 0.7661        | 0.6741         | 0.7748        | 0.8544                 | 0.8774                | 0.9441              | 0.8160           | 0.9784       | 0.8991          | 0.6656         | 0.9748       | 0.8970         | 0.9630       | 0.7704         | 0.8112              | 0.8096           | 0.9813   | 0.8484       | 0.9108       | 0.5660   | 0.5429    | 0.5432   | 0.6432            | 0.7370           | 0.9145         | 0.6393      | 0.9408  | 0.7631     | 0.5321    | 0.9365  | 0.6980    | 0.7964  | 0.6506    | 0.4226         | 0.7024      |
+
+
+### Framework versions
+
+- Transformers 4.48.0
+- Pytorch 2.1.2+cu121
+- Datasets 3.2.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,112 @@
+{
+  "_name_or_path": "nvidia/segformer-b2-finetuned-cityscapes-1024-1024",
+  "architectures": [
+    "SegformerForSemanticSegmentation"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout_prob": 0.1,
+  "decoder_hidden_size": 768,
+  "depths": [
+    3,
+    4,
+    6,
+    3
+  ],
+  "downsampling_rates": [
+    1,
+    4,
+    8,
+    16
+  ],
+  "drop_path_rate": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_sizes": [
+    64,
+    128,
+    320,
+    512
+  ],
+  "id2label": {
+    "0": "road",
+    "1": "sidewalk",
+    "2": "building",
+    "3": "wall",
+    "4": "fence",
+    "5": "pole",
+    "6": "traffic light",
+    "7": "traffic sign",
+    "8": "vegetation",
+    "9": "terrain",
+    "10": "sky",
+    "11": "person",
+    "12": "rider",
+    "13": "car",
+    "14": "truck",
+    "15": "bus",
+    "16": "train",
+    "17": "motorcycle",
+    "18": "bicycle"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "label2id": {
+    "bicycle": 18,
+    "building": 2,
+    "bus": 15,
+    "car": 13,
+    "fence": 4,
+    "motorcycle": 17,
+    "person": 11,
+    "pole": 5,
+    "rider": 12,
+    "road": 0,
+    "sidewalk": 1,
+    "sky": 10,
+    "terrain": 9,
+    "traffic light": 6,
+    "traffic sign": 7,
+    "train": 16,
+    "truck": 14,
+    "vegetation": 8,
+    "wall": 3
+  },
+  "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": "4.48.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a8a806e824725f786bb81f09eef1721baa178da928e1ea262fddeafdc424424
+size 109496316

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8ab05211697a749bf1b80accbc690531ecceac9620f76cef5130eaa9dfd65f0
+size 5368