SegFormer-model-flood-images

README.md

@@ -0,0 +1,74 @@
+---
+library_name: transformers
+license: other
+base_model: nvidia/segformer-b0-finetuned-ade-512-512
+tags:
+- generated_from_trainer
+model-index:
+- name: segformer-b0-segments-sidewalk-finetuned
+  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-segments-sidewalk-finetuned
+
+This model is a fine-tuned version of [nvidia/segformer-b0-finetuned-ade-512-512](https://huggingface.co/nvidia/segformer-b0-finetuned-ade-512-512) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2634
+- Mean Iou: 0.4383
+- Mean Accuracy: 0.8765
+- Overall Accuracy: 0.8765
+- Accuracy Background: nan
+- Accuracy Target: 0.8765
+- Iou Background: 0.0
+- Iou Target: 0.8765
+
+## 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: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Background | Accuracy Target | Iou Background | Iou Target |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:-------------------:|:---------------:|:--------------:|:----------:|
+| 0.4747        | 1.0   | 26   | 0.3768          | 0.4287   | 0.8573        | 0.8573           | nan                 | 0.8573          | 0.0            | 0.8573     |
+| 0.3193        | 2.0   | 52   | 0.3138          | 0.4198   | 0.8395        | 0.8395           | nan                 | 0.8395          | 0.0            | 0.8395     |
+| 0.2792        | 3.0   | 78   | 0.2899          | 0.4318   | 0.8636        | 0.8636           | nan                 | 0.8636          | 0.0            | 0.8636     |
+| 0.2569        | 4.0   | 104  | 0.2723          | 0.4202   | 0.8405        | 0.8405           | nan                 | 0.8405          | 0.0            | 0.8405     |
+| 0.2504        | 5.0   | 130  | 0.2634          | 0.4383   | 0.8765        | 0.8765           | nan                 | 0.8765          | 0.0            | 0.8765     |
+| 0.2294        | 6.0   | 156  | 0.2572          | 0.4292   | 0.8584        | 0.8584           | nan                 | 0.8584          | 0.0            | 0.8584     |
+| 0.2337        | 7.0   | 182  | 0.2567          | 0.4292   | 0.8584        | 0.8584           | nan                 | 0.8584          | 0.0            | 0.8584     |
+| 0.2255        | 8.0   | 208  | 0.2546          | 0.4354   | 0.8707        | 0.8707           | nan                 | 0.8707          | 0.0            | 0.8707     |
+| 0.2213        | 9.0   | 234  | 0.2557          | 0.4299   | 0.8597        | 0.8597           | nan                 | 0.8597          | 0.0            | 0.8597     |
+| 0.2203        | 10.0  | 260  | 0.2552          | 0.4372   | 0.8744        | 0.8744           | nan                 | 0.8744          | 0.0            | 0.8744     |
+
+
+### Framework versions
+
+- Transformers 4.46.3
+- Pytorch 2.5.1+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

config.json

@@ -0,0 +1,78 @@
+{
+  "_name_or_path": "nvidia/segformer-b0-finetuned-ade-512-512",
+  "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": "background",
+    "1": "target"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "label2id": {
+    "background": 0,
+    "target": 1
+  },
+  "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": "4.46.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56fd23b071113b79cc12b842fada33e5e9b6a1899c512f2cf8e67e1e01287f30
+size 14884776

preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "do_normalize": true,
+  "do_reduce_labels": false,
+  "do_rescale": false,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "SegformerImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 512,
+    "width": 512
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5825a8e093ecc1c1c05ec75cbf1e8c142d7b188882986764f8a06830bc1120d
+size 5304