best_model.pt

README.md

@@ -0,0 +1,84 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: windowz_test-020625
+  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-020625
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Model Preparation Time: 0.001
+- Accuracy: 0.9521
+- F1: 0.9483
+- Iou: 0.9076
+- Contour Dice: 0.9035
+- Per Class Metrics: {0: {'f1': 0.97101, 'iou': 0.94365, 'accuracy': 0.95541, 'contour_dice': 0.97101}, 1: {'f1': 0.90428, 'iou': 0.82528, 'accuracy': 0.95685, 'contour_dice': 0.90428}, 2: {'f1': 0.27674, 'iou': 0.16059, 'accuracy': 0.99191, 'contour_dice': 0.27674}}
+- Loss: 0.4842
+
+## 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: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Model Preparation Time |        | Dice   | Class Metrics                                                                                                                                                                                                                                          | Validation Loss |
+|:-------------:|:------:|:----:|:----------------------:|:------:|:------:|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:---------------:|
+| 1.3502        | 0.0501 | 257  | 0.001                  | 0.5644 | 0.0674 | {0: {'f1': 0.85985, 'iou': 0.75416, 'accuracy': 0.75632, 'contour_dice': 0.85985}, 1: {'f1': 3e-05, 'iou': 2e-05, 'accuracy': 0.75751, 'contour_dice': 3e-05}, 2: {'f1': 0.03477, 'iou': 0.01769, 'accuracy': 0.98186, 'contour_dice': 0.03477}}       | 1.0501          |
+| 1.2779        | 0.1003 | 514  | 0.001                  | 0.5614 | 0.0110 | {0: {'f1': 0.85654, 'iou': 0.74908, 'accuracy': 0.74943, 'contour_dice': 0.85654}, 1: {'f1': 0.0, 'iou': 0.0, 'accuracy': 0.7575, 'contour_dice': 0.0}, 2: {'f1': 0.18607, 'iou': 0.10258, 'accuracy': 0.99115, 'contour_dice': 0.18607}}              | 0.9869          |
+| 1.2058        | 0.1504 | 771  | 0.001                  | 0.5601 | 0.0024 | {0: {'f1': 0.85601, 'iou': 0.74826, 'accuracy': 0.74834, 'contour_dice': 0.85601}, 1: {'f1': 0.00043, 'iou': 0.00021, 'accuracy': 0.75755, 'contour_dice': 0.00043}, 2: {'f1': 0.04908, 'iou': 0.02516, 'accuracy': 0.99076, 'contour_dice': 0.04908}} | 0.9181          |
+| 1.1158        | 0.2005 | 1028 | 0.001                  | 0.5610 | 0.0074 | {0: {'f1': 0.85634, 'iou': 0.74877, 'accuracy': 0.74901, 'contour_dice': 0.85634}, 1: {'f1': 0.00103, 'iou': 0.00052, 'accuracy': 0.75763, 'contour_dice': 0.00103}, 2: {'f1': 0.14378, 'iou': 0.07746, 'accuracy': 0.99122, 'contour_dice': 0.14378}} | 0.8743          |
+| 1.0785        | 0.2507 | 1285 | 0.001                  | 0.5614 | 0.0087 | {0: {'f1': 0.85643, 'iou': 0.74892, 'accuracy': 0.74919, 'contour_dice': 0.85643}, 1: {'f1': 0.00618, 'iou': 0.0031, 'accuracy': 0.75825, 'contour_dice': 0.00618}, 2: {'f1': 0.07155, 'iou': 0.0371, 'accuracy': 0.99093, 'contour_dice': 0.07155}}   | 0.8316          |
+| 1.0445        | 0.3008 | 1542 | 0.001                  | 0.7385 | 0.6122 | {0: {'f1': 0.9132, 'iou': 0.84027, 'accuracy': 0.85815, 'contour_dice': 0.9132}, 1: {'f1': 0.619, 'iou': 0.44823, 'accuracy': 0.8647, 'contour_dice': 0.619}, 2: {'f1': 0.22291, 'iou': 0.12543, 'accuracy': 0.99173, 'contour_dice': 0.22291}}        | 0.7703          |
+| 1.0092        | 0.3510 | 1799 | 0.001                  | 0.7510 | 0.6389 | {0: {'f1': 0.91749, 'iou': 0.84755, 'accuracy': 0.86567, 'contour_dice': 0.91749}, 1: {'f1': 0.64415, 'iou': 0.47509, 'accuracy': 0.87163, 'contour_dice': 0.64415}, 2: {'f1': 0.31734, 'iou': 0.18859, 'accuracy': 0.99231, 'contour_dice': 0.31734}} | 0.7823          |
+| 0.9676        | 0.4011 | 2056 | 0.001                  | 0.7371 | 0.6147 | {0: {'f1': 0.91344, 'iou': 0.84066, 'accuracy': 0.85863, 'contour_dice': 0.91344}, 1: {'f1': 0.60393, 'iou': 0.43259, 'accuracy': 0.86089, 'contour_dice': 0.60393}, 2: {'f1': 0.52376, 'iou': 0.3548, 'accuracy': 0.99253, 'contour_dice': 0.52376}}  | 0.8004          |
+| 0.9308        | 0.4512 | 2313 | 0.001                  | 0.8564 | 0.8337 | {0: {'f1': 0.95377, 'iou': 0.91162, 'accuracy': 0.92764, 'contour_dice': 0.95377}, 1: {'f1': 0.83301, 'iou': 0.71381, 'accuracy': 0.9292, 'contour_dice': 0.83301}, 2: {'f1': 0.25373, 'iou': 0.1453, 'accuracy': 0.9918, 'contour_dice': 0.25373}}    | 0.7535          |
+| 0.9187        | 0.5014 | 2570 | 0.001                  | 0.868  | 0.8442 | {0: {'f1': 0.95642, 'iou': 0.91649, 'accuracy': 0.93189, 'contour_dice': 0.95642}, 1: {'f1': 0.8514, 'iou': 0.74124, 'accuracy': 0.93689, 'contour_dice': 0.8514}, 2: {'f1': 0.43757, 'iou': 0.28006, 'accuracy': 0.99306, 'contour_dice': 0.43757}}   | 0.7077          |
+| 0.8916        | 0.5515 | 2827 | 0.001                  | 0.8656 | 0.8447 | {0: {'f1': 0.95636, 'iou': 0.91636, 'accuracy': 0.93186, 'contour_dice': 0.95636}, 1: {'f1': 0.84316, 'iou': 0.72885, 'accuracy': 0.93331, 'contour_dice': 0.84316}, 2: {'f1': 0.5173, 'iou': 0.34889, 'accuracy': 0.9935, 'contour_dice': 0.5173}}    | 0.6670          |
+| 0.8723        | 0.6016 | 3084 | 0.001                  | 0.9221 | 0.9210 | {0: {'f1': 0.97564, 'iou': 0.95244, 'accuracy': 0.96276, 'contour_dice': 0.97564}, 1: {'f1': 0.92036, 'iou': 0.85247, 'accuracy': 0.9635, 'contour_dice': 0.92036}, 2: {'f1': 0.46566, 'iou': 0.30349, 'accuracy': 0.99314, 'contour_dice': 0.46566}}  | 0.6549          |
+| 0.8761        | 0.6518 | 3341 | 0.001                  | 0.7678 | 0.7651 | {0: {'f1': 0.90349, 'iou': 0.82397, 'accuracy': 0.86319, 'contour_dice': 0.90349}, 1: {'f1': 0.76222, 'iou': 0.6158, 'accuracy': 0.86427, 'contour_dice': 0.76222}, 2: {'f1': 0.35206, 'iou': 0.21364, 'accuracy': 0.99248, 'contour_dice': 0.35206}}  | 0.7303          |
+| 0.869         | 0.7019 | 3598 | 0.001                  | 0.9259 | 0.9263 | {0: {'f1': 0.97721, 'iou': 0.95544, 'accuracy': 0.96519, 'contour_dice': 0.97721}, 1: {'f1': 0.92398, 'iou': 0.85871, 'accuracy': 0.96506, 'contour_dice': 0.92398}, 2: {'f1': 0.47308, 'iou': 0.30983, 'accuracy': 0.99326, 'contour_dice': 0.47308}} | 0.6818          |
+| 0.8526        | 0.7520 | 3855 | 0.001                  | 0.9455 | 0.9507 | {0: {'f1': 0.98427, 'iou': 0.96902, 'accuracy': 0.97615, 'contour_dice': 0.98427}, 1: {'f1': 0.94744, 'iou': 0.90013, 'accuracy': 0.97519, 'contour_dice': 0.94744}, 2: {'f1': 0.38871, 'iou': 0.24124, 'accuracy': 0.99266, 'contour_dice': 0.38871}} | 0.5164          |
+| 0.8487        | 0.8022 | 4112 | 0.001                  | 0.8958 | 0.8869 | {0: {'f1': 0.96679, 'iou': 0.93572, 'accuracy': 0.94866, 'contour_dice': 0.96679}, 1: {'f1': 0.88802, 'iou': 0.7986, 'accuracy': 0.95052, 'contour_dice': 0.88802}, 2: {'f1': 0.36537, 'iou': 0.22352, 'accuracy': 0.99239, 'contour_dice': 0.36537}}  | 0.5553          |
+| 0.8519        | 0.8523 | 4369 | 0.001                  | 0.9236 | 0.9231 | {0: {'f1': 0.97639, 'iou': 0.95387, 'accuracy': 0.96388, 'contour_dice': 0.97639}, 1: {'f1': 0.92437, 'iou': 0.85937, 'accuracy': 0.9653, 'contour_dice': 0.92437}, 2: {'f1': 0.29738, 'iou': 0.17466, 'accuracy': 0.99214, 'contour_dice': 0.29738}}  | 0.4860          |
+| 0.8331        | 0.9025 | 4626 | 0.001                  | 0.9076 | 0.9035 | {0: {'f1': 0.97101, 'iou': 0.94365, 'accuracy': 0.95541, 'contour_dice': 0.97101}, 1: {'f1': 0.90428, 'iou': 0.82528, 'accuracy': 0.95685, 'contour_dice': 0.90428}, 2: {'f1': 0.27674, 'iou': 0.16059, 'accuracy': 0.99191, 'contour_dice': 0.27674}} | 0.4842          |
+| 0.8357        | 0.9526 | 4883 | 0.001                  | 0.8881 | 0.8770 | {0: {'f1': 0.96409, 'iou': 0.93067, 'accuracy': 0.94441, 'contour_dice': 0.96409}, 1: {'f1': 0.87736, 'iou': 0.78151, 'accuracy': 0.94613, 'contour_dice': 0.87736}, 2: {'f1': 0.40324, 'iou': 0.25254, 'accuracy': 0.99246, 'contour_dice': 0.40324}} | 0.5096          |
+
+
+### 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 sha256:6b78ba10a5c1b9064a664658a29d3afa2c413804b393b6668f4fa2da25ef4de5
+size 2188724

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1ae6012ddf95afdd3d8358098f85b8b1832ad99a3f879410d3a6f1c08736340
+size 5240