e1010101/vit-384-tongue-image-segmented

README.md

@@ -0,0 +1,69 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google/vit-base-patch16-384
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+model-index:
+- name: segmented-augmented
+  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. -->
+
+# segmented-augmented
+
+This model is a fine-tuned version of [google/vit-base-patch16-384](https://huggingface.co/google/vit-base-patch16-384) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5815
+- Precision: 0.8308
+- Recall: 0.9136
+- F1: 0.8703
+
+## 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: 2e-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: linear
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|
+| 0.081         | 1.0   | 327  | 0.3693          | 0.8464    | 0.8970 | 0.8710 |
+| 0.0151        | 2.0   | 654  | 0.4906          | 0.8171    | 0.8904 | 0.8521 |
+| 0.0066        | 3.0   | 981  | 0.5194          | 0.8416    | 0.9003 | 0.8700 |
+| 0.0029        | 4.0   | 1308 | 0.5671          | 0.8308    | 0.9136 | 0.8703 |
+| 0.0026        | 5.0   | 1635 | 0.5815          | 0.8308    | 0.9136 | 0.8703 |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.1+cu121
+- Datasets 3.0.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/vit-base-patch16-384",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Crack",
+    "1": "Red-Dots",
+    "2": "Toothmark"
+  },
+  "image_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Crack": 0,
+    "Red-Dots": 1,
+    "Toothmark": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "problem_type": "multi_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02616418f496e68096355079c88fa418fb3450bed6e5b6e082b8fde9cfc1f80f
+size 344394412

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70ac198c798bc36337ed7da7a7f8f72274e7eceaf855e3258de169a46d0cd6e7
+size 5176