Upload folder using huggingface_hub

README.md

@@ -0,0 +1,22 @@
+---
+library_name: keras-hub
+---
+This is a [`ViT` model](https://keras.io/api/keras_hub/models/vi_t) uploaded using the KerasHub library and can be used with JAX, TensorFlow, and PyTorch backends.
+This model is related to a `ImageClassifier` task.
+
+Model config:
+* **name:** vi_t_backbone
+* **trainable:** True
+* **image_shape:** [384, 384, 3]
+* **patch_size:** 32
+* **num_layers:** 24
+* **num_heads:** 16
+* **hidden_dim:** 1024
+* **mlp_dim:** 4096
+* **dropout_rate:** 0.0
+* **attention_dropout:** 0.0
+* **layer_norm_epsilon:** 1e-06
+* **use_mha_bias:** True
+* **use_mlp_bias:** True
+
+This model card has been generated automatically and should be completed by the model author. See [Model Cards documentation](https://huggingface.co/docs/hub/model-cards) for more information.

config.json

@@ -0,0 +1,24 @@
+{
+    "module": "keras_hub.src.models.vit.vit_backbone",
+    "class_name": "ViTBackbone",
+    "config": {
+        "name": "vi_t_backbone",
+        "trainable": true,
+        "image_shape": [
+            384,
+            384,
+            3
+        ],
+        "patch_size": 32,
+        "num_layers": 24,
+        "num_heads": 16,
+        "hidden_dim": 1024,
+        "mlp_dim": 4096,
+        "dropout_rate": 0.0,
+        "attention_dropout": 0.0,
+        "layer_norm_epsilon": 1e-06,
+        "use_mha_bias": true,
+        "use_mlp_bias": true
+    },
+    "registered_name": "keras_hub>ViTBackbone"
+}

image_converter.json

@@ -0,0 +1,35 @@
+{
+    "module": "keras_hub.src.models.vit.vit_image_converter",
+    "class_name": "ViTImageConverter",
+    "config": {
+        "name": "vi_t_image_converter",
+        "trainable": true,
+        "dtype": {
+            "module": "keras",
+            "class_name": "DTypePolicy",
+            "config": {
+                "name": "float32"
+            },
+            "registered_name": null
+        },
+        "image_size": [
+            384,
+            384
+        ],
+        "scale": 0.00392156862745098,
+        "offset": null,
+        "interpolation": "bilinear",
+        "crop_to_aspect_ratio": true,
+        "norm_mean": [
+            0.5,
+            0.5,
+            0.5
+        ],
+        "norm_std": [
+            0.5,
+            0.5,
+            0.5
+        ]
+    },
+    "registered_name": "keras_hub>ViTImageConverter"
+}

metadata.json

@@ -0,0 +1,9 @@
+{
+    "keras_version": "3.7.0",
+    "keras_hub_version": "0.19.0",
+    "parameter_count": 305607680,
+    "date_saved": "2024-12-17@15:46:36",
+    "tasks": [
+        "ImageClassifier"
+    ]
+}

model.weights.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69492f5a30d118d434b6b7fd04a6108070bbafd8511b50cd417f63b67d65c225
+size 1223296824

preprocessor.json

@@ -0,0 +1,53 @@
+{
+    "module": "keras_hub.src.models.vit.vit_image_classifier_preprocessor",
+    "class_name": "ViTImageClassifierPreprocessor",
+    "config": {
+        "name": "vi_t_image_classifier_preprocessor",
+        "trainable": true,
+        "dtype": {
+            "module": "keras",
+            "class_name": "DTypePolicy",
+            "config": {
+                "name": "float32"
+            },
+            "registered_name": null
+        },
+        "image_converter": {
+            "module": "keras_hub.src.models.vit.vit_image_converter",
+            "class_name": "ViTImageConverter",
+            "config": {
+                "name": "vi_t_image_converter",
+                "trainable": true,
+                "dtype": {
+                    "module": "keras",
+                    "class_name": "DTypePolicy",
+                    "config": {
+                        "name": "float32"
+                    },
+                    "registered_name": null
+                },
+                "image_size": [
+                    384,
+                    384
+                ],
+                "scale": 0.00392156862745098,
+                "offset": null,
+                "interpolation": "bilinear",
+                "crop_to_aspect_ratio": true,
+                "norm_mean": [
+                    0.5,
+                    0.5,
+                    0.5
+                ],
+                "norm_std": [
+                    0.5,
+                    0.5,
+                    0.5
+                ]
+            },
+            "registered_name": "keras_hub>ViTImageConverter"
+        },
+        "config_file": "preprocessor.json"
+    },
+    "registered_name": "keras_hub>ViTImageClassifierPreprocessor"
+}

task.json

@@ -0,0 +1,90 @@
+{
+    "module": "keras_hub.src.models.vit.vit_image_classifier",
+    "class_name": "ViTImageClassifier",
+    "config": {
+        "backbone": {
+            "module": "keras_hub.src.models.vit.vit_backbone",
+            "class_name": "ViTBackbone",
+            "config": {
+                "name": "vi_t_backbone",
+                "trainable": true,
+                "image_shape": [
+                    384,
+                    384,
+                    3
+                ],
+                "patch_size": 32,
+                "num_layers": 24,
+                "num_heads": 16,
+                "hidden_dim": 1024,
+                "mlp_dim": 4096,
+                "dropout_rate": 0.0,
+                "attention_dropout": 0.0,
+                "layer_norm_epsilon": 1e-06,
+                "use_mha_bias": true,
+                "use_mlp_bias": true
+            },
+            "registered_name": "keras_hub>ViTBackbone"
+        },
+        "preprocessor": {
+            "module": "keras_hub.src.models.vit.vit_image_classifier_preprocessor",
+            "class_name": "ViTImageClassifierPreprocessor",
+            "config": {
+                "name": "vi_t_image_classifier_preprocessor",
+                "trainable": true,
+                "dtype": {
+                    "module": "keras",
+                    "class_name": "DTypePolicy",
+                    "config": {
+                        "name": "float32"
+                    },
+                    "registered_name": null
+                },
+                "image_converter": {
+                    "module": "keras_hub.src.models.vit.vit_image_converter",
+                    "class_name": "ViTImageConverter",
+                    "config": {
+                        "name": "vi_t_image_converter",
+                        "trainable": true,
+                        "dtype": {
+                            "module": "keras",
+                            "class_name": "DTypePolicy",
+                            "config": {
+                                "name": "float32"
+                            },
+                            "registered_name": null
+                        },
+                        "image_size": [
+                            384,
+                            384
+                        ],
+                        "scale": 0.00392156862745098,
+                        "offset": null,
+                        "interpolation": "bilinear",
+                        "crop_to_aspect_ratio": true,
+                        "norm_mean": [
+                            0.5,
+                            0.5,
+                            0.5
+                        ],
+                        "norm_std": [
+                            0.5,
+                            0.5,
+                            0.5
+                        ]
+                    },
+                    "registered_name": "keras_hub>ViTImageConverter"
+                },
+                "config_file": "preprocessor.json"
+            },
+            "registered_name": "keras_hub>ViTImageClassifierPreprocessor"
+        },
+        "name": "vi_t_image_classifier",
+        "num_classes": 1000,
+        "pooling": "token",
+        "activation": null,
+        "dropout": 0.0,
+        "intermediate_dim": null
+    },
+    "registered_name": "keras_hub>ViTImageClassifier"
+}

task.weights.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c65350772c0ea83325f277b5ba72c5a53dd8b7f1ce07003f42008fcdc4072899
+size 1227412992