best_model.pt

README.md

@@ -0,0 +1,73 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: windowz_test-022625
+  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. -->
+
+# windowz_test-022625
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Accuracy: 0.9908
+- F1: 0.9910
+- Iou: 0.9832
+- Per Class Metrics: {0: {'f1': 0.99751, 'iou': 0.99504, 'accuracy': 0.99628}, 1: {'f1': 0.98091, 'iou': 0.96254, 'accuracy': 0.99081}, 2: {'f1': 0.73081, 'iou': 0.5758, 'accuracy': 0.99448}}
+- Loss: 0.0169
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 100
+
+### Training results
+
+| Training Loss | Epoch | Step   |        | Class Metrics                                                                                                                                                               | Validation Loss |
+|:-------------:|:-----:|:------:|:------:|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:---------------:|
+| 0.4586        | 5.0   | 12815  | 0.9710 | {0: {'f1': 0.99385, 'iou': 0.98778, 'accuracy': 0.99081}, 1: {'f1': 0.96879, 'iou': 0.93947, 'accuracy': 0.98478}, 2: {'f1': 0.62073, 'iou': 0.45004, 'accuracy': 0.99365}} | 0.0890          |
+| 0.4363        | 10.0  | 25630  | 0.9810 | {0: {'f1': 0.99729, 'iou': 0.9946, 'accuracy': 0.99595}, 1: {'f1': 0.97943, 'iou': 0.95969, 'accuracy': 0.99}, 2: {'f1': 0.6238, 'iou': 0.45327, 'accuracy': 0.99404}}      | 0.0220          |
+| 0.4148        | 15.0  | 38445  | 0.9785 | {0: {'f1': 0.99619, 'iou': 0.9924, 'accuracy': 0.99428}, 1: {'f1': 0.97538, 'iou': 0.95195, 'accuracy': 0.98824}, 2: {'f1': 0.71793, 'iou': 0.55998, 'accuracy': 0.99388}}  | 0.0593          |
+| 0.3935        | 20.0  | 51260  | 0.9743 | {0: {'f1': 0.99419, 'iou': 0.98845, 'accuracy': 0.99126}, 1: {'f1': 0.97367, 'iou': 0.94869, 'accuracy': 0.9874}, 2: {'f1': 0.67815, 'iou': 0.51303, 'accuracy': 0.99437}}  | 0.0229          |
+| 0.3755        | 25.0  | 64075  | 0.9826 | {0: {'f1': 0.99767, 'iou': 0.99534, 'accuracy': 0.99651}, 1: {'f1': 0.9796, 'iou': 0.96001, 'accuracy': 0.9902}, 2: {'f1': 0.71337, 'iou': 0.55445, 'accuracy': 0.99367}}   | 0.0187          |
+| 0.3834        | 30.0  | 76890  | 0.9814 | {0: {'f1': 0.99714, 'iou': 0.9943, 'accuracy': 0.99572}, 1: {'f1': 0.97847, 'iou': 0.95784, 'accuracy': 0.98967}, 2: {'f1': 0.71791, 'iou': 0.55995, 'accuracy': 0.99391}}  | 0.0175          |
+| 0.3609        | 35.0  | 89705  | 0.9832 | {0: {'f1': 0.99751, 'iou': 0.99504, 'accuracy': 0.99628}, 1: {'f1': 0.98091, 'iou': 0.96254, 'accuracy': 0.99081}, 2: {'f1': 0.73081, 'iou': 0.5758, 'accuracy': 0.99448}}  | 0.0169          |
+| 0.364         | 40.0  | 102520 | 0.9815 | {0: {'f1': 0.99756, 'iou': 0.99513, 'accuracy': 0.99635}, 1: {'f1': 0.97769, 'iou': 0.95635, 'accuracy': 0.98933}, 2: {'f1': 0.70736, 'iou': 0.54722, 'accuracy': 0.99295}} | 0.0210          |
+| 0.3561        | 45.0  | 115335 | 0.9857 | {0: {'f1': 0.99789, 'iou': 0.9958, 'accuracy': 0.99685}, 1: {'f1': 0.98385, 'iou': 0.96822, 'accuracy': 0.99221}, 2: {'f1': 0.77212, 'iou': 0.62883, 'accuracy': 0.99536}}  | 0.0208          |
+| 0.3714        | 50.0  | 128150 | 0.9843 | {0: {'f1': 0.99769, 'iou': 0.99539, 'accuracy': 0.99654}, 1: {'f1': 0.98205, 'iou': 0.96473, 'accuracy': 0.99135}, 2: {'f1': 0.75937, 'iou': 0.61209, 'accuracy': 0.99479}} | 0.0170          |
+
+
+### Framework versions
+
+- Transformers 4.45.0
+- Pytorch 2.5.1+cu124
+- Datasets 2.21.0
+- Tokenizers 0.20.3

config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "UNETForSegmentation"
+  ],
+  "dim": 224,
+  "hidden_act": "gelu",
+  "hidden_size": 256,
+  "img_size": 128,
+  "intermediate_size": 1024,
+  "is_causal": false,
+  "k": 2,
+  "model_type": "Unet",
+  "n_filts": 4,
+  "num_attention_heads": 8,
+  "num_channels": 3,
+  "num_classes": 3,
+  "num_hidden_layers": 6,
+  "num_layers": 2,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "t": 2,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ce3f067b392776ac7157fe4900761b0fa9abbd906fee67cf580aaa07b307dcb
+size 2188724

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:553776a611c5811e0dcc9b040bb1da0cd9cdb7e5053d1c3d889eec34daf7779b
+size 5240