Upload 9 files

README.md

@@ -0,0 +1,74 @@
+---
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- image-classification
+- vision
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+model-index:
+- name: output
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: imagefolder
+      type: imagefolder
+      config: default
+      split: train
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9668874172185431
+---
+
+<!-- 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. -->
+
+# output
+
+This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1172
+- Accuracy: 0.9669
+
+## 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: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.38.0.dev0
+- Pytorch 2.2.0+cpu
+- Datasets 2.17.0
+- Tokenizers 0.15.1

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9668874172185431,
+    "eval_loss": 0.11718238145112991,
+    "eval_runtime": 161.4495,
+    "eval_samples_per_second": 3.741,
+    "eval_steps_per_second": 0.471,
+    "train_loss": 0.2442077654544438,
+    "train_runtime": 16583.1029,
+    "train_samples_per_second": 0.619,
+    "train_steps_per_second": 0.077
+}

config.json

@@ -0,0 +1,33 @@
+{
+  "_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": "no_pothole",
+    "1": "pothole"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "no_pothole": "0",
+    "pothole": "1"
+  },
+  "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": "4.38.0.dev0"
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9668874172185431,
+    "eval_loss": 0.11718238145112991,
+    "eval_runtime": 161.4495,
+    "eval_samples_per_second": 3.741,
+    "eval_steps_per_second": 0.471
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccb2e422b34b1bf09d4e5695b10167aa257ea5bb2a476279bc96c03a050871d2
+size 343223968

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
+  }
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.2442077654544438,
+    "train_runtime": 16583.1029,
+    "train_samples_per_second": 0.619,
+    "train_steps_per_second": 0.077
+}

trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1284,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.17,
+      "learning_rate": 3.0529595015576326e-05,
+      "loss": 0.3272,
+      "step": 500
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 1.1059190031152649e-05,
+      "loss": 0.214,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "step": 1284,
+      "total_flos": 7.955327653834015e+17,
+      "train_loss": 0.2442077654544438,
+      "train_runtime": 16583.1029,
+      "train_samples_per_second": 0.619,
+      "train_steps_per_second": 0.077
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1284,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 7.955327653834015e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eee21a3ed8629189fee9c5567bbd985627753a07960974e2ee4a2ce96646b3d3
+size 4984