Upload TFViTForImageClassification

README.md

@@ -0,0 +1,71 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- generated_from_keras_callback
+model-index:
+- name: Entrnal_5class_agumm_last_newV6_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_5class_agumm_last_newV6_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: 0.0410
+- Train Accuracy: 0.9612
+- Train Top-3-accuracy: 0.9962
+- Validation Loss: 0.3703
+- Validation Accuracy: 0.9623
+- Validation Top-3-accuracy: 0.9963
+- Epoch: 12
+
+## 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': 1209, '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 |
+|:----------:|:--------------:|:--------------------:|:---------------:|:-------------------:|:-------------------------:|:-----:|
+| 1.0109     | 0.5898         | 0.8913               | 0.5771          | 0.7468              | 0.9576                    | 0     |
+| 0.4103     | 0.7997         | 0.9708               | 0.4029          | 0.8329              | 0.9786                    | 1     |
+| 0.2249     | 0.8581         | 0.9827               | 0.3677          | 0.8769              | 0.9857                    | 2     |
+| 0.1584     | 0.8905         | 0.9877               | 0.3730          | 0.9010              | 0.9893                    | 3     |
+| 0.1164     | 0.9097         | 0.9904               | 0.3957          | 0.9169              | 0.9913                    | 4     |
+| 0.0841     | 0.9231         | 0.9920               | 0.3896          | 0.9285              | 0.9927                    | 5     |
+| 0.0676     | 0.9331         | 0.9932               | 0.3718          | 0.9373              | 0.9937                    | 6     |
+| 0.0561     | 0.9408         | 0.9941               | 0.3701          | 0.9440              | 0.9944                    | 7     |
+| 0.0500     | 0.9468         | 0.9947               | 0.3691          | 0.9493              | 0.9949                    | 8     |
+| 0.0461     | 0.9516         | 0.9952               | 0.3698          | 0.9535              | 0.9954                    | 9     |
+| 0.0435     | 0.9554         | 0.9956               | 0.3694          | 0.9570              | 0.9958                    | 10    |
+| 0.0418     | 0.9585         | 0.9959               | 0.3705          | 0.9598              | 0.9961                    | 11    |
+| 0.0410     | 0.9612         | 0.9962               | 0.3703          | 0.9623              | 0.9963                    | 12    |
+
+
+### 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": "Cataract",
+    "1": "DR",
+    "2": "Glaucoma",
+    "3": "RVO",
+    "4": "normal"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Cataract": "0",
+    "DR": "1",
+    "Glaucoma": "2",
+    "RVO": "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:dd48f856c40334af25bc3df3e5037898a3cb1513cf4a66ce67284fcbe23b1b60
+size 343478968