Duplicate from mansee/vit-base-patch16-224-blur_vs_clean

Co-authored-by: mansi agrawal <[email protected]>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,80 @@
+---
+license: apache-2.0
+base_model: google/vit-base-patch16-224
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+model-index:
+- name: vit-base-patch16-224-blur_vs_clean
+  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: 0.9753602975360297
+---
+
+<!-- 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. -->
+
+# vit-base-patch16-224-blur_vs_clean
+
+This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0714
+- Accuracy: 0.9754
+
+## 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: 32
+- eval_batch_size: 32
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.0539        | 1.0   | 151  | 0.1078          | 0.9596   |
+| 0.0611        | 2.0   | 302  | 0.0846          | 0.9698   |
+| 0.049         | 3.0   | 453  | 0.0714          | 0.9754   |
+
+
+### Framework versions
+
+- Transformers 4.31.0
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.0
+- Tokenizers 0.13.3

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9753602975360297,
+    "eval_loss": 0.07140230387449265,
+    "eval_runtime": 36.6123,
+    "eval_samples_per_second": 58.751,
+    "eval_steps_per_second": 1.857,
+    "total_flos": 4.4917456860202107e+18,
+    "train_loss": 0.10242866058618028,
+    "train_runtime": 2277.1585,
+    "train_samples_per_second": 25.492,
+    "train_steps_per_second": 0.199
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "blur",
+    "1": "clean"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "blur": 0,
+    "clean": 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": "4.31.0"
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9753602975360297,
+    "eval_loss": 0.07140230387449265,
+    "eval_runtime": 36.6123,
+    "eval_samples_per_second": 58.751,
+    "eval_steps_per_second": 1.857
+}

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:da7d071d532e36801883879b878f6df27b57804ae5ee369600940e4aa8ef7dec
+size 343268717

runs/Jul25_10-54-59_628a4864d230/events.out.tfevents.1690282520.628a4864d230.1652.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c0ebd397a1a996d0375390949607a48bf9ce53d1a54662ca13951543b36cdb3
+size 12450

runs/Jul25_10-54-59_628a4864d230/events.out.tfevents.1690284864.628a4864d230.1652.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05e27ab569f6910e61eb4b0a5a16aba4127584c3391b7fa99be7a3e6b1581175
+size 411

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 4.4917456860202107e+18,
+    "train_loss": 0.10242866058618028,
+    "train_runtime": 2277.1585,
+    "train_samples_per_second": 25.492,
+    "train_steps_per_second": 0.199
+}

trainer_state.json

@@ -0,0 +1,322 @@
+{
+  "best_metric": 0.9753602975360297,
+  "best_model_checkpoint": "vit-base-patch16-224-blur_vs_clean/checkpoint-453",
+  "epoch": 2.9950413223140497,
+  "global_step": 453,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.0869565217391305e-05,
+      "loss": 0.7653,
+      "step": 10
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 2.173913043478261e-05,
+      "loss": 0.6297,
+      "step": 20
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 3.260869565217392e-05,
+      "loss": 0.4462,
+      "step": 30
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.347826086956522e-05,
+      "loss": 0.2414,
+      "step": 40
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.950859950859951e-05,
+      "loss": 0.1249,
+      "step": 50
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.8280098280098285e-05,
+      "loss": 0.1293,
+      "step": 60
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 4.705159705159705e-05,
+      "loss": 0.1083,
+      "step": 70
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.582309582309582e-05,
+      "loss": 0.0917,
+      "step": 80
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.4594594594594596e-05,
+      "loss": 0.1057,
+      "step": 90
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 4.336609336609337e-05,
+      "loss": 0.0803,
+      "step": 100
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 4.213759213759214e-05,
+      "loss": 0.0666,
+      "step": 110
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 4.0909090909090915e-05,
+      "loss": 0.0832,
+      "step": 120
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 3.968058968058968e-05,
+      "loss": 0.0867,
+      "step": 130
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.845208845208845e-05,
+      "loss": 0.0812,
+      "step": 140
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.7223587223587226e-05,
+      "loss": 0.0539,
+      "step": 150
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9595536959553695,
+      "eval_loss": 0.10777629911899567,
+      "eval_runtime": 34.5907,
+      "eval_samples_per_second": 62.184,
+      "eval_steps_per_second": 1.966,
+      "step": 151
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 3.5995085995085995e-05,
+      "loss": 0.0753,
+      "step": 160
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 3.476658476658477e-05,
+      "loss": 0.0619,
+      "step": 170
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 3.3538083538083545e-05,
+      "loss": 0.0605,
+      "step": 180
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 3.2309582309582306e-05,
+      "loss": 0.0473,
+      "step": 190
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 3.108108108108108e-05,
+      "loss": 0.0672,
+      "step": 200
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 2.9852579852579853e-05,
+      "loss": 0.0626,
+      "step": 210
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 2.8624078624078625e-05,
+      "loss": 0.0704,
+      "step": 220
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 2.73955773955774e-05,
+      "loss": 0.0517,
+      "step": 230
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 2.616707616707617e-05,
+      "loss": 0.0494,
+      "step": 240
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 2.493857493857494e-05,
+      "loss": 0.0603,
+      "step": 250
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 2.371007371007371e-05,
+      "loss": 0.0678,
+      "step": 260
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 2.2481572481572483e-05,
+      "loss": 0.0506,
+      "step": 270
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 2.1253071253071255e-05,
+      "loss": 0.0556,
+      "step": 280
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 2.0024570024570026e-05,
+      "loss": 0.0687,
+      "step": 290
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 1.8796068796068798e-05,
+      "loss": 0.0611,
+      "step": 300
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9697814969781497,
+      "eval_loss": 0.08457668125629425,
+      "eval_runtime": 33.7533,
+      "eval_samples_per_second": 63.727,
+      "eval_steps_per_second": 2.015,
+      "step": 302
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 1.756756756756757e-05,
+      "loss": 0.0444,
+      "step": 310
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 1.6339066339066338e-05,
+      "loss": 0.0417,
+      "step": 320
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 1.5110565110565111e-05,
+      "loss": 0.0496,
+      "step": 330
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 1.3882063882063885e-05,
+      "loss": 0.045,
+      "step": 340
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 1.2653562653562653e-05,
+      "loss": 0.0496,
+      "step": 350
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 1.1425061425061426e-05,
+      "loss": 0.0481,
+      "step": 360
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 1.0196560196560196e-05,
+      "loss": 0.0329,
+      "step": 370
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 8.96805896805897e-06,
+      "loss": 0.0424,
+      "step": 380
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 7.73955773955774e-06,
+      "loss": 0.0274,
+      "step": 390
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 6.511056511056511e-06,
+      "loss": 0.0394,
+      "step": 400
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 5.282555282555283e-06,
+      "loss": 0.0522,
+      "step": 410
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 4.0540540540540545e-06,
+      "loss": 0.0331,
+      "step": 420
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 2.8255528255528258e-06,
+      "loss": 0.0275,
+      "step": 430
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 1.5970515970515972e-06,
+      "loss": 0.0374,
+      "step": 440
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 3.6855036855036856e-07,
+      "loss": 0.049,
+      "step": 450
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9753602975360297,
+      "eval_loss": 0.07140230387449265,
+      "eval_runtime": 35.4449,
+      "eval_samples_per_second": 60.686,
+      "eval_steps_per_second": 1.918,
+      "step": 453
+    },
+    {
+      "epoch": 3.0,
+      "step": 453,
+      "total_flos": 4.4917456860202107e+18,
+      "train_loss": 0.10242866058618028,
+      "train_runtime": 2277.1585,
+      "train_samples_per_second": 25.492,
+      "train_steps_per_second": 0.199
+    }
+  ],
+  "max_steps": 453,
+  "num_train_epochs": 3,
+  "total_flos": 4.4917456860202107e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8204357a3067bc16d26a8a14db6038d71d2606014b061abff7124c14eb58004
+size 4027