Add models

README.md

@@ -1,7 +1,74 @@
 ---
-library_name: keras
-pipeline_tag: image-classification
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
 tags:
-- medical
-- not-for-all-audiences
----
+- image-classification
+- vision
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+model-index:
+- name: outputs
+  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: 1.0
+---
+
+<!-- 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. -->
+
+# outputs
+
+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: 0.0596
+- Accuracy: 1.0
+
+## 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 4.32.0.dev0
+- Pytorch 2.0.1+cu117
+- Datasets 2.14.4
+- Tokenizers 0.13.3

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 1.0,
+    "eval_loss": 0.05963269993662834,
+    "eval_runtime": 1.6852,
+    "eval_samples_per_second": 162.591,
+    "eval_steps_per_second": 20.769,
+    "train_loss": 0.3140656472891057,
+    "train_runtime": 90.7552,
+    "train_samples_per_second": 51.303,
+    "train_steps_per_second": 6.413
+}

checkpoint-500/config.json

@@ -0,0 +1,41 @@
+{
+  "_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": "Foi_Thong",
+    "1": "Hang_Kra_Rog_Phu_Phan_ST1",
+    "2": "Hang_Suea_Sakonnakhon_TT1",
+    "3": "Kroeng_Krawia",
+    "4": "Tanao_Si_Kan_Khaw_WA1",
+    "5": "Tanao_Si_Kan_Sang_RD1"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Foi_Thong": "0",
+    "Hang_Kra_Rog_Phu_Phan_ST1": "1",
+    "Hang_Suea_Sakonnakhon_TT1": "2",
+    "Kroeng_Krawia": "3",
+    "Tanao_Si_Kan_Khaw_WA1": "4",
+    "Tanao_Si_Kan_Sang_RD1": "5"
+  },
+  "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": "4.32.0.dev0"
+}

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72f3654e6af7f483c08dd67d48ce10da8ebd7839bc8a3b9d81674153eaec1b7c
+size 686593029

checkpoint-500/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
+  }
+}

checkpoint-500/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ddf69503dc4492ff8c2ac0737829c1f91d6ea6c16eb9449190bb01edb597c42
+size 343281005

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f6931b8dc8099fb9bacdeef960d70faa4de518663359bc8435aa7ee67cf4c5c
+size 14575

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27da3fb10c98c3a5cb0797163ccb140b215f681ceb86a19ebdf1188fd3ccb947
+size 627

checkpoint-500/trainer_state.json

@@ -0,0 +1,25 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.5773195876288657,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.58,
+      "learning_rate": 7.0446735395189e-06,
+      "loss": 0.3528,
+      "step": 500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 582,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 3.0997907103744e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9e5ff1e2863c010b1ac4302ddaa8d909ea89a6225cbdc9ccc7a7035d9faf64f
+size 4027

config.json

@@ -0,0 +1,41 @@
+{
+  "_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": "Foi_Thong",
+    "1": "Hang_Kra_Rog_Phu_Phan_ST1",
+    "2": "Hang_Suea_Sakonnakhon_TT1",
+    "3": "Kroeng_Krawia",
+    "4": "Tanao_Si_Kan_Khaw_WA1",
+    "5": "Tanao_Si_Kan_Sang_RD1"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Foi_Thong": "0",
+    "Hang_Kra_Rog_Phu_Phan_ST1": "1",
+    "Hang_Suea_Sakonnakhon_TT1": "2",
+    "Kroeng_Krawia": "3",
+    "Tanao_Si_Kan_Khaw_WA1": "4",
+    "Tanao_Si_Kan_Sang_RD1": "5"
+  },
+  "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": "4.32.0.dev0"
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 1.0,
+    "eval_loss": 0.05963269993662834,
+    "eval_runtime": 1.6852,
+    "eval_samples_per_second": 162.591,
+    "eval_steps_per_second": 20.769
+}

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 sha256:25b61b8857371e420457d7aa7fa95858f9c625af452d8c491e78b0adab3556ca
+size 343281005

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.3140656472891057,
+    "train_runtime": 90.7552,
+    "train_samples_per_second": 51.303,
+    "train_steps_per_second": 6.413
+}

trainer_state.json

@@ -0,0 +1,34 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 582,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.58,
+      "learning_rate": 7.0446735395189e-06,
+      "loss": 0.3528,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "step": 582,
+      "total_flos": 3.6081563868758016e+17,
+      "train_loss": 0.3140656472891057,
+      "train_runtime": 90.7552,
+      "train_samples_per_second": 51.303,
+      "train_steps_per_second": 6.413
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 582,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 3.6081563868758016e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9e5ff1e2863c010b1ac4302ddaa8d909ea89a6225cbdc9ccc7a7035d9faf64f
+size 4027