segmentation-lungs

README.md

@@ -0,0 +1,71 @@
+---
+library_name: transformers
+license: other
+base_model: nvidia/segformer-b0-finetuned-ade-512-512
+tags:
+- generated_from_trainer
+model-index:
+- name: segformer-b0-segments-lungs-xray
+  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-lungs-xray
+
+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: 0.0589
+- Mean Iou: 0.9509
+- Mean Accuracy: 0.9747
+- Overall Accuracy: 0.9814
+- Accuracy Background: 0.9877
+- Accuracy Target: 0.9617
+- Iou Background: 0.9758
+- Iou Target: 0.9260
+
+## 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: 4
+- eval_batch_size: 4
+- 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: 7
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Background | Accuracy Target | Iou Background | Iou Target |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:-------------------:|:---------------:|:--------------:|:----------:|
+| 0.1417        | 1.0   | 123  | 0.1330          | 0.9172   | 0.9657        | 0.9673           | 0.9688              | 0.9626          | 0.9574         | 0.8770     |
+| 0.0957        | 2.0   | 246  | 0.0860          | 0.9425   | 0.9680        | 0.9782           | 0.9878              | 0.9481          | 0.9717         | 0.9133     |
+| 0.0889        | 3.0   | 369  | 0.0743          | 0.9418   | 0.9734        | 0.9777           | 0.9817              | 0.9650          | 0.9709         | 0.9128     |
+| 0.076         | 4.0   | 492  | 0.0635          | 0.9494   | 0.9724        | 0.9809           | 0.9889              | 0.9559          | 0.9751         | 0.9237     |
+| 0.0621        | 5.0   | 615  | 0.0603          | 0.9508   | 0.9734        | 0.9814           | 0.9890              | 0.9578          | 0.9758         | 0.9259     |
+| 0.0653        | 6.0   | 738  | 0.0589          | 0.9509   | 0.9747        | 0.9814           | 0.9877              | 0.9617          | 0.9758         | 0.9260     |
+| 0.0593        | 7.0   | 861  | 0.0587          | 0.9507   | 0.9748        | 0.9813           | 0.9875              | 0.9622          | 0.9757         | 0.9258     |
+
+
+### Framework versions
+
+- Transformers 4.46.3
+- Pytorch 2.5.1+cu121
+- Datasets 3.2.0
+- 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 sha256:2700c4dce57c54fd1c302f556c4cae7f096c68dc16c44c63e08576ed78942b5d
+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": 256,
+    "width": 256
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a925ad2d0530907165fd758b795f87479fc3f29eea4aa84f30673190197efe50
+size 5304