Upload folder using huggingface_hub

README.md

@@ -1,3 +1,81 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- image-classification
+- computer-vision
+- skincare
+- vision-transformer
+datasets:
+- custom
+metrics:
+- accuracy
+- f1
+pipeline_tag: image-classification
+---
+
+# skincare-detection
+
+## Model Description
+
+This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) for skincare image classification.
+
+## Model Performance
+
+- **Accuracy**: N/A
+- **F1 Score**: N/A
+- **Precision**: N/A
+- **Recall**: N/A
+
+## Training Details
+
+### Training Data
+Custom dataset with 200 training samples
+
+### Training Hyperparameters
+
+- Learning rate: 2e-4
+- Batch size: 32
+- Number of epochs: 12
+- Optimizer: Adam
+- Scheduler: Linear with warmup
+
+### Classes
+Classes: acne, eczema, normal, rosacea
+
+## Usage
+
+```python
+from transformers import ViTImageProcessor, ViTForImageClassification
+from PIL import Image
+import torch
+
+# Load model and processor
+processor = ViTImageProcessor.from_pretrained('0xnu/skincare-detection')
+model = ViTForImageClassification.from_pretrained('0xnu/skincare-detection')
+
+# Process image
+image = Image.open('path_to_your_image.jpg')
+inputs = processor(images=image, return_tensors="pt")
+
+# Make prediction
+with torch.no_grad():
+    outputs = model(**inputs)
+    logits = outputs.logits
+    predicted_class_id = logits.argmax().item()
+    predicted_label = model.config.id2label[predicted_class_id]
+
+print(f"Predicted class: {predicted_label}")
+```
+
+## Limitations and Bias
+
+- The model performance depends on the quality and diversity of training data
+- May not generalise well to skincare images significantly different from training distribution
+- Evaluate model performance on your specific use case before deployment
+
+## Training Environment
+
+- Framework: Transformers 4.38.2
+- PyTorch: 2.1.2
+- Hardware: GPU/CPU

checkpoint-24/config.json

@@ -0,0 +1,37 @@
+{
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "acne",
+    "1": "eczema",
+    "2": "normal",
+    "3": "rosacea"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "acne": 0,
+    "eczema": 1,
+    "normal": 2,
+    "rosacea": 3
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "pooler_act": "tanh",
+  "pooler_output_size": 768,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.0"
+}

checkpoint-24/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5823126bb2dcf845e0d5b5a9ef85febfef7bd6461e0fcda29ed0adfee64c79ef
+size 343230128

checkpoint-24/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca47e9e34386883c7e0568a3b50479626f4ad9ee2a0d96efa8e34d04ca1537d4
+size 686576011

checkpoint-24/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e38e4bded6fa666a78b369223010c84f8eafdd4ce4069224aa6f2854b4222440
+size 14455

checkpoint-24/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02366c6584197b626fb76cdc3670f43abab526eee56710041f674a166cf81a4b
+size 1465

checkpoint-24/trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 12.0,
+  "eval_steps": 50,
+  "global_step": 24,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.9926398992538452,
+      "learning_rate": 0.00014285714285714287,
+      "loss": 0.8337,
+      "step": 10
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.41569486260414124,
+      "learning_rate": 4.761904761904762e-05,
+      "loss": 0.1567,
+      "step": 20
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 24,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 12,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.859841088487424e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-24/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4aed3420e473a8800e471f723bc84c39200216f80b1882c067e8e9691f167105
+size 5713

config.json

@@ -0,0 +1,37 @@
+{
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "acne",
+    "1": "eczema",
+    "2": "normal",
+    "3": "rosacea"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "acne": 0,
+    "eczema": 1,
+    "normal": 2,
+    "rosacea": 3
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "pooler_act": "tanh",
+  "pooler_output_size": 768,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5823126bb2dcf845e0d5b5a9ef85febfef7bd6461e0fcda29ed0adfee64c79ef
+size 343230128

preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "do_convert_rgb": null,
+  "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
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4aed3420e473a8800e471f723bc84c39200216f80b1882c067e8e9691f167105
+size 5713

training_results.json

@@ -0,0 +1,8 @@
+{
+  "train_runtime": 211.1149,
+  "train_samples_per_second": 11.368,
+  "train_steps_per_second": 0.114,
+  "total_flos": 1.859841088487424e+17,
+  "train_loss": 0.4300013507405917,
+  "epoch": 12.0
+}