Upload TFViTForImageClassification

README.md

@@ -0,0 +1,65 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- generated_from_keras_callback
+model-index:
+- name: Entrnal_eyes_data_5class_RVO_resize_224_model
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information Keras had access to. You should
+probably proofread and complete it, then remove this comment. -->
+
+# Entrnal_eyes_data_5class_RVO_resize_224_model
+
+This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.0870
+- Train Accuracy: 0.9372
+- Train Top-3-accuracy: 0.9944
+- Validation Loss: 0.2468
+- Validation Accuracy: 0.9406
+- Validation Top-3-accuracy: 0.9948
+- Epoch: 6
+
+## 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:
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 784, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
+- training_precision: float32
+
+### Training results
+
+| Train Loss | Train Accuracy | Train Top-3-accuracy | Validation Loss | Validation Accuracy | Validation Top-3-accuracy | Epoch |
+|:----------:|:--------------:|:--------------------:|:---------------:|:-------------------:|:-------------------------:|:-----:|
+| 0.9323     | 0.6128         | 0.8870               | 0.4850          | 0.7838              | 0.9644                    | 0     |
+| 0.3507     | 0.8315         | 0.9758               | 0.3223          | 0.8593              | 0.9822                    | 1     |
+| 0.2174     | 0.8787         | 0.9858               | 0.2710          | 0.8925              | 0.9883                    | 2     |
+| 0.1573     | 0.9034         | 0.9899               | 0.3544          | 0.9108              | 0.9911                    | 3     |
+| 0.1231     | 0.9172         | 0.9920               | 0.2527          | 0.9235              | 0.9928                    | 4     |
+| 0.0963     | 0.9287         | 0.9934               | 0.2485          | 0.9333              | 0.9940                    | 5     |
+| 0.0870     | 0.9372         | 0.9944               | 0.2468          | 0.9406              | 0.9948                    | 6     |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- TensorFlow 2.15.1
+- Datasets 3.0.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224-in21k",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "DP",
+    "1": "RVO",
+    "2": "cataract",
+    "3": "glaucoma",
+    "4": "normal"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "DP": "0",
+    "RVO": "1",
+    "cataract": "2",
+    "glaucoma": "3",
+    "normal": "4"
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "qkv_bias": true,
+  "transformers_version": "4.44.2"
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77bb2922d5aa005903456227ca0cfc154a609e716e1c3663d20346f8e6b991a6
+size 343478968