Upload 9 files

README.md

@@ -0,0 +1,80 @@
+---
+license: apache-2.0
+base_model: microsoft/swin-tiny-patch4-window7-224
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+model-index:
+- name: swin-tiny-patch4-window7-224-finetuned-eurosat
+  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: 0.9991525423728813
+---
+
+<!-- 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. -->
+
+# Face-Mask-Detection
+
+This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0051
+- Accuracy: 0.9992
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.0344        | 1.0   | 83   | 0.0051          | 0.9992   |
+| 0.0112        | 2.0   | 166  | 0.0052          | 0.9983   |
+| 0.0146        | 3.0   | 249  | 0.0045          | 0.9992   |
+
+
+### Framework versions
+
+- Transformers 4.34.0
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.5
+- Tokenizers 0.14.0

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9991525423728813,
+    "eval_loss": 0.005057646427303553,
+    "eval_runtime": 7.9885,
+    "eval_samples_per_second": 147.712,
+    "eval_steps_per_second": 4.632,
+    "total_flos": 7.913152653537116e+17,
+    "train_loss": 0.04654426268305645,
+    "train_runtime": 513.1593,
+    "train_samples_per_second": 62.039,
+    "train_steps_per_second": 0.485
+}

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "microsoft/swin-tiny-patch4-window7-224",
+  "architectures": [
+    "SwinForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "depths": [
+    2,
+    2,
+    6,
+    2
+  ],
+  "drop_path_rate": 0.1,
+  "embed_dim": 96,
+  "encoder_stride": 32,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "WithMask",
+    "1": "WithoutMask"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "label2id": {
+    "WithMask": 0,
+    "WithoutMask": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "mlp_ratio": 4.0,
+  "model_type": "swin",
+  "num_channels": 3,
+  "num_heads": [
+    3,
+    6,
+    12,
+    24
+  ],
+  "num_layers": 4,
+  "out_features": [
+    "stage4"
+  ],
+  "out_indices": [
+    4
+  ],
+  "patch_size": 4,
+  "path_norm": true,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4"
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0",
+  "use_absolute_embeddings": false,
+  "window_size": 7
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9991525423728813,
+    "eval_loss": 0.005057646427303553,
+    "eval_runtime": 7.9885,
+    "eval_samples_per_second": 147.712,
+    "eval_steps_per_second": 4.632
+}

preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "ViTImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 3,
+  "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:c6187b21a4e24e1538bdb67e505224b3a7b7cc3205e02630d170dda0545deeae
+size 110394865

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 7.913152653537116e+17,
+    "train_loss": 0.04654426268305645,
+    "train_runtime": 513.1593,
+    "train_samples_per_second": 62.039,
+    "train_steps_per_second": 0.485
+}

trainer_state.json

@@ -0,0 +1,199 @@
+{
+  "best_metric": 0.9991525423728813,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-83",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 249,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12,
+      "learning_rate": 2e-05,
+      "loss": 0.4995,
+      "step": 10
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4e-05,
+      "loss": 0.1624,
+      "step": 20
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.888392857142857e-05,
+      "loss": 0.0535,
+      "step": 30
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 4.665178571428572e-05,
+      "loss": 0.0346,
+      "step": 40
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.4419642857142854e-05,
+      "loss": 0.0452,
+      "step": 50
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 4.21875e-05,
+      "loss": 0.0238,
+      "step": 60
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.9955357142857144e-05,
+      "loss": 0.0239,
+      "step": 70
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 3.7723214285714286e-05,
+      "loss": 0.0344,
+      "step": 80
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9991525423728813,
+      "eval_loss": 0.005057646427303553,
+      "eval_runtime": 8.2623,
+      "eval_samples_per_second": 142.817,
+      "eval_steps_per_second": 4.478,
+      "step": 83
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 3.5491071428571435e-05,
+      "loss": 0.032,
+      "step": 90
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 3.325892857142857e-05,
+      "loss": 0.017,
+      "step": 100
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 3.102678571428572e-05,
+      "loss": 0.0119,
+      "step": 110
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 2.8794642857142857e-05,
+      "loss": 0.0215,
+      "step": 120
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 2.6562500000000002e-05,
+      "loss": 0.0219,
+      "step": 130
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 2.4330357142857144e-05,
+      "loss": 0.0293,
+      "step": 140
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 2.2098214285714286e-05,
+      "loss": 0.0202,
+      "step": 150
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1.9866071428571427e-05,
+      "loss": 0.0112,
+      "step": 160
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9983050847457627,
+      "eval_loss": 0.005177544895559549,
+      "eval_runtime": 8.4063,
+      "eval_samples_per_second": 140.37,
+      "eval_steps_per_second": 4.401,
+      "step": 166
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 1.7633928571428573e-05,
+      "loss": 0.0088,
+      "step": 170
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 1.5401785714285715e-05,
+      "loss": 0.0193,
+      "step": 180
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 1.3169642857142858e-05,
+      "loss": 0.0102,
+      "step": 190
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 1.09375e-05,
+      "loss": 0.0083,
+      "step": 200
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 8.705357142857143e-06,
+      "loss": 0.0077,
+      "step": 210
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 6.473214285714287e-06,
+      "loss": 0.0097,
+      "step": 220
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 4.241071428571429e-06,
+      "loss": 0.0207,
+      "step": 230
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 2.0089285714285715e-06,
+      "loss": 0.0146,
+      "step": 240
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9991525423728813,
+      "eval_loss": 0.004469145555049181,
+      "eval_runtime": 8.3109,
+      "eval_samples_per_second": 141.983,
+      "eval_steps_per_second": 4.452,
+      "step": 249
+    },
+    {
+      "epoch": 3.0,
+      "step": 249,
+      "total_flos": 7.913152653537116e+17,
+      "train_loss": 0.04654426268305645,
+      "train_runtime": 513.1593,
+      "train_samples_per_second": 62.039,
+      "train_steps_per_second": 0.485
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 249,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 7.913152653537116e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff30a20c1c0ab8cfa2214952514c508a9394fca8722e9de0ea7d9ce6fd809b1
+size 4155