Upload 4 files

README.md

@@ -0,0 +1,17 @@
+---
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- image-classification
+---
+
+This is the app introduction image classifier of the following paper:
+```bibtex
+@misc{wei2024guing,
+      title={GUing: A Mobile GUI Search Engine using a Vision-Language Model}, 
+      author={Jialiang Wei and Anne-Lise Courbis and Thomas Lambolais and Binbin Xu and Pierre Louis Bernard and Gérard Dray and Walid Maalej},
+      year={2024},
+      eprint={2405.00145},
+      archivePrefix={arXiv}
+}
+```
+Please note that the model can only be used for academic purpose.

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224-in21k",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "finetuning_task": "image-classification",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": 0,
+    "1": 1,
+    "2": 2
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": "0",
+    "1": "1",
+    "2": "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": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.1"
+}

preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30adea1703644589858354d3cf62f23d52d5a585b29d3980c5eeac4030ef85be
+size 343271789