Upload folder using huggingface_hub

README.md

@@ -0,0 +1,137 @@
+---
+license: apache-2.0
+datasets:
+- strangerguardhf/Tooth-Agenesis-6_Types
+language:
+- en
+base_model:
+- google/siglip2-base-patch16-512
+pipeline_tag: image-classification
+library_name: transformers
+tags:
+- tooth
+- SigLIP2
+- chemistry
+- biology
+- medical
+- Calculus
+- Mouth Ulcer
+- hypodontia
+- Tooth Discoloration
+- Gingivitis
+- tooth-agenesis
+---
+
+![123.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/9_mjg7bzNcQT-Ifx-ATmH.png)
+
+# tooth-agenesis-siglip2
+
+> tooth-agenesis-siglip2 is a vision-language encoder model fine-tuned from `google/siglip2-base-patch16-512` for **multi-class image classification**. It is trained to detect various **dental anomalies and conditions** such as **Calculus**, **Caries**, **Gingivitis**, **Mouth Ulcer**, **Tooth Discoloration**, and **Hypodontia**. The model uses the `SiglipForImageClassification` architecture.
+
+> \[!note]
+> SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
+> [https://arxiv.org/pdf/2502.14786](https://arxiv.org/pdf/2502.14786)
+
+```py
+Classification Report:
+                     precision    recall  f1-score   support
+
+           Calculus     0.6640    0.7623    0.7098      1296
+             Caries     0.9525    0.9558    0.9541      2601
+         Gingivitis     0.8496    0.7842    0.8156      2349
+        Mouth Ulcer     0.9939    0.9893    0.9916      2806
+Tooth Discoloration     0.9314    0.9757    0.9530      2017
+         hypodontia     0.9983    0.9161    0.9554      1251
+
+           accuracy                         0.9096     12320
+          macro avg     0.8983    0.8972    0.8966     12320
+       weighted avg     0.9132    0.9096    0.9105     12320
+```
+
+![download.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/vCoLKevXThpp6GhYCvoCe.png)
+
+---
+
+## Label Space: 6 Classes
+
+```
+Class 0: Calculus  
+Class 1: Caries  
+Class 2: Gingivitis  
+Class 3: Mouth Ulcer  
+Class 4: Tooth Discoloration  
+Class 5: hypodontia
+```
+
+---
+
+## Install Dependencies
+
+```bash
+pip install -q transformers torch pillow gradio hf_xet
+```
+
+---
+
+## Inference Code
+
+```python
+import gradio as gr
+from transformers import AutoImageProcessor, SiglipForImageClassification
+from PIL import Image
+import torch
+
+# Load model and processor
+model_name = "prithivMLmods/tooth-agenesis-siglip2"  # Update with actual model name on Hugging Face
+model = SiglipForImageClassification.from_pretrained(model_name)
+processor = AutoImageProcessor.from_pretrained(model_name)
+
+# Updated label mapping
+id2label = {
+    "0": "Calculus",
+    "1": "Caries",
+    "2": "Gingivitis",
+    "3": "Mouth Ulcer",
+    "4": "Tooth Discoloration",
+    "5": "hypodontia"
+}
+
+def classify_image(image):
+    image = Image.fromarray(image).convert("RGB")
+    inputs = processor(images=image, return_tensors="pt")
+
+    with torch.no_grad():
+        outputs = model(**inputs)
+        logits = outputs.logits
+        probs = torch.nn.functional.softmax(logits, dim=1).squeeze().tolist()
+
+    prediction = {
+        id2label[str(i)]: round(probs[i], 3) for i in range(len(probs))
+    }
+
+    return prediction
+
+# Gradio Interface
+iface = gr.Interface(
+    fn=classify_image,
+    inputs=gr.Image(type="numpy"),
+    outputs=gr.Label(num_top_classes=6, label="Dental Condition Classification"),
+    title="Tooth Agenesis Detection",
+    description="Upload a dental image to detect conditions such as Calculus, Caries, Gingivitis, Mouth Ulcer, Tooth Discoloration, or Hypodontia."
+)
+
+if __name__ == "__main__":
+    iface.launch()
+```
+
+---
+
+## Intended Use
+
+`tooth-agenesis-siglip2` is designed for:
+
+* **Dental Diagnosis Support** – Assists dentists and clinicians in identifying common dental conditions from images.
+* **Oral Health Monitoring** – A tool for regular monitoring of dental health in clinical or remote settings.
+* **Tele-dentistry** – Enables automated screening in virtual consultations and rural healthcare setups.
+* **Research and Education** – Useful for academic institutions and training platforms for demonstrating AI in dental diagnostics.
+* **Early Detection** – Helps identify oral health issues early to prevent progression. 

checkpoint-385/config.json

@@ -0,0 +1,54 @@
+{
+  "architectures": [
+    "SiglipForImageClassification"
+  ],
+  "id2label": {
+    "0": "Calculus",
+    "1": "Caries",
+    "2": "Gingivitis",
+    "3": "Mouth Ulcer",
+    "4": "Tooth Discoloration",
+    "5": "hypodontia"
+  },
+  "initializer_factor": 1.0,
+  "label2id": {
+    "Calculus": 0,
+    "Caries": 1,
+    "Gingivitis": 2,
+    "Mouth Ulcer": 3,
+    "Tooth Discoloration": 4,
+    "hypodontia": 5
+  },
+  "model_type": "siglip",
+  "problem_type": "single_label_classification",
+  "text_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 768,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-06,
+    "max_position_embeddings": 64,
+    "model_type": "siglip_text_model",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12,
+    "projection_size": 768,
+    "torch_dtype": "float32",
+    "vocab_size": 256000
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.0",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 768,
+    "image_size": 224,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 12,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "patch_size": 16,
+    "torch_dtype": "float32"
+  }
+}

checkpoint-385/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52ae922fdcd72c41820710051b8899171c77749421f0cf52195f5480a5e86ec5
+size 371580296

checkpoint-385/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c24ea3ed574fc4e9c0b28cffd579c776c41c177f2df27d9495966cc12d1f1e8
+size 686580346

checkpoint-385/preprocessor_config.json

@@ -0,0 +1,24 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "SiglipImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "SiglipProcessor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

checkpoint-385/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16b54ce6fd1c1a696526f20e141e670796f8dafe3b5fa3f0170630f591063c47
+size 14244

checkpoint-385/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88749df3b9c03f705cff9eb98de5f9eb8338f8b1e1f28ed21f063079c8f2170a
+size 1064

checkpoint-385/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_global_step": 385,
+  "best_metric": 0.4734131693840027,
+  "best_model_checkpoint": "siglip2-finetune-full/checkpoint-385",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 385,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.806737012987013,
+      "eval_loss": 0.4734131693840027,
+      "eval_model_preparation_time": 0.0024,
+      "eval_runtime": 170.3731,
+      "eval_samples_per_second": 72.312,
+      "eval_steps_per_second": 9.039,
+      "step": 385
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 770,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0319019352621056e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-385/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:206d195b28a5a4e1f61804a2eec06b109a4be9fa8d841f4d552fca404cebe15f
+size 5304

checkpoint-770/config.json

@@ -0,0 +1,54 @@
+{
+  "architectures": [
+    "SiglipForImageClassification"
+  ],
+  "id2label": {
+    "0": "Calculus",
+    "1": "Caries",
+    "2": "Gingivitis",
+    "3": "Mouth Ulcer",
+    "4": "Tooth Discoloration",
+    "5": "hypodontia"
+  },
+  "initializer_factor": 1.0,
+  "label2id": {
+    "Calculus": 0,
+    "Caries": 1,
+    "Gingivitis": 2,
+    "Mouth Ulcer": 3,
+    "Tooth Discoloration": 4,
+    "hypodontia": 5
+  },
+  "model_type": "siglip",
+  "problem_type": "single_label_classification",
+  "text_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 768,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-06,
+    "max_position_embeddings": 64,
+    "model_type": "siglip_text_model",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12,
+    "projection_size": 768,
+    "torch_dtype": "float32",
+    "vocab_size": 256000
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.0",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 768,
+    "image_size": 224,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 12,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "patch_size": 16,
+    "torch_dtype": "float32"
+  }
+}

checkpoint-770/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:050405b5d29610cb6c0a9a4008b486bad93864817e9d4f6c9e901f6df4e606cd
+size 371580296

checkpoint-770/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e80777f4d487951c583c74539c6d8361faf5d62c853a6ff24e88f4d7f85a99e
+size 686580346

checkpoint-770/preprocessor_config.json

@@ -0,0 +1,24 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "SiglipImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "SiglipProcessor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

checkpoint-770/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ca30a322288606f938ab113b96242751c166b4bd034fa2700e7ddb17ee3d469
+size 14244

checkpoint-770/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e214f8d6ea3674b15247be20b661fa60b42e2e15e99757de3d5c4a36546d8f56
+size 1064

checkpoint-770/trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_global_step": 770,
+  "best_metric": 0.21896059811115265,
+  "best_model_checkpoint": "siglip2-finetune-full/checkpoint-770",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 770,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.806737012987013,
+      "eval_loss": 0.4734131693840027,
+      "eval_model_preparation_time": 0.0024,
+      "eval_runtime": 170.3731,
+      "eval_samples_per_second": 72.312,
+      "eval_steps_per_second": 9.039,
+      "step": 385
+    },
+    {
+      "epoch": 1.2987012987012987,
+      "grad_norm": 9.846982955932617,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.8037,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9095779220779221,
+      "eval_loss": 0.21896059811115265,
+      "eval_model_preparation_time": 0.0024,
+      "eval_runtime": 171.2991,
+      "eval_samples_per_second": 71.921,
+      "eval_steps_per_second": 8.99,
+      "step": 770
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 770,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.0638038705242112e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-770/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:206d195b28a5a4e1f61804a2eec06b109a4be9fa8d841f4d552fca404cebe15f
+size 5304

config.json

@@ -0,0 +1,54 @@
+{
+  "architectures": [
+    "SiglipForImageClassification"
+  ],
+  "id2label": {
+    "0": "Calculus",
+    "1": "Caries",
+    "2": "Gingivitis",
+    "3": "Mouth Ulcer",
+    "4": "Tooth Discoloration",
+    "5": "hypodontia"
+  },
+  "initializer_factor": 1.0,
+  "label2id": {
+    "Calculus": 0,
+    "Caries": 1,
+    "Gingivitis": 2,
+    "Mouth Ulcer": 3,
+    "Tooth Discoloration": 4,
+    "hypodontia": 5
+  },
+  "model_type": "siglip",
+  "problem_type": "single_label_classification",
+  "text_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 768,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-06,
+    "max_position_embeddings": 64,
+    "model_type": "siglip_text_model",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12,
+    "projection_size": 768,
+    "torch_dtype": "float32",
+    "vocab_size": 256000
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.0",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 768,
+    "image_size": 224,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 12,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "patch_size": 16,
+    "torch_dtype": "float32"
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:050405b5d29610cb6c0a9a4008b486bad93864817e9d4f6c9e901f6df4e606cd
+size 371580296

preprocessor_config.json

@@ -0,0 +1,24 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "SiglipImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "SiglipProcessor",
+  "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 sha256:206d195b28a5a4e1f61804a2eec06b109a4be9fa8d841f4d552fca404cebe15f
+size 5304