Duplicate from prithivMLmods/Gender-Classifier-Mini

Co-authored-by: Prithiv Sakthi <prithivMLmods@users.noreply.huggingface.co>

.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

README.md

@@ -0,0 +1,100 @@
+---
+license: apache-2.0
+language:
+- en
+base_model:
+- google/siglip2-base-patch16-224
+pipeline_tag: image-classification
+library_name: transformers
+tags:
+- gender
+- male
+- female
+- siglip2
+datasets:
+- myvision/gender-classification
+---
+
+![2.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/gfvc6sCbh9saiVnczYH2c.png)
+
+# **Gender-Classifier-Mini**
+
+> **Gender-Classifier-Mini** is an image classification vision-language encoder model fine-tuned from **google/siglip2-base-patch16-224** for a single-label classification task. It is designed to classify images based on gender using the **SiglipForImageClassification** architecture.  
+
+```py
+Accuracy: 0.9720
+F1 Score: 0.9720
+
+Classification Report:
+              precision    recall  f1-score   support
+
+    Female ♀     0.9660    0.9796    0.9727      2549
+      Male ♂     0.9785    0.9641    0.9712      2451
+
+    accuracy                         0.9720      5000
+   macro avg     0.9722    0.9718    0.9720      5000
+weighted avg     0.9721    0.9720    0.9720      5000
+```
+
+![Untitled.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/MNO7bk_1wr5lvfyTDnhjF.png)
+
+The model categorizes images into two classes:
+- **Class 0:** "Female ♀"
+- **Class 1:** "Male ♂"
+
+# **Run with Transformers🤗**
+
+```python
+!pip install -q transformers torch pillow gradio
+```
+
+```python
+import gradio as gr
+from transformers import AutoImageProcessor
+from transformers import SiglipForImageClassification
+from transformers.image_utils import load_image
+from PIL import Image
+import torch
+
+# Load model and processor
+model_name = "prithivMLmods/Gender-Classifier-Mini"
+model = SiglipForImageClassification.from_pretrained(model_name)
+processor = AutoImageProcessor.from_pretrained(model_name)
+
+def gender_classification(image):
+    """Predicts gender category for an 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()
+    
+    labels = {"0": "Female ♀", "1": "Male ♂"}
+    predictions = {labels[str(i)]: round(probs[i], 3) for i in range(len(probs))}
+    
+    return predictions
+
+# Create Gradio interface
+iface = gr.Interface(
+    fn=gender_classification,
+    inputs=gr.Image(type="numpy"),
+    outputs=gr.Label(label="Prediction Scores"),
+    title="Gender Classification",
+    description="Upload an image to classify its gender."
+)
+
+# Launch the app
+if __name__ == "__main__":
+    iface.launch()
+```
+
+# **Intended Use:**  
+
+The **Gender-Classifier-Mini** model is designed to classify images into gender categories. Potential use cases include:  
+
+- **Demographic Analysis:** Assisting in understanding gender distribution in datasets.
+- **Face Recognition Systems:** Enhancing identity verification processes.
+- **Marketing & Advertising:** Personalizing content based on demographic insights.
+- **Healthcare & Research:** Supporting gender-based analysis in medical imaging.

checkpoint-157/config.json

@@ -0,0 +1,46 @@
+{
+  "architectures": [
+    "SiglipForImageClassification"
+  ],
+  "id2label": {
+    "0": "Female \u2640",
+    "1": "Male \u2642"
+  },
+  "initializer_factor": 1.0,
+  "label2id": {
+    "Female \u2640": 0,
+    "Male \u2642": 1
+  },
+  "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": "4.51.0.dev0",
+  "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-157/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b3c881ec1fe495b6b7b22e0736bb670c36abef535d9173a427e5cbe50ffb9eb
+size 371567992

checkpoint-157/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e42ca61096460c1b7078d91e3d07d3c3b5ddc67fe516b44fdf9643760658696
+size 686555770

checkpoint-157/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-157/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86d5603fb9476ef375dada75dcc320d16423a8b7cade08e44ab0230cd7431cd5
+size 14244

checkpoint-157/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4e52ea243618241f112cfa55bc1203d9492a008fab26d507445786f4e9c80e8
+size 1064

checkpoint-157/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_global_step": 157,
+  "best_metric": 0.11236772686243057,
+  "best_model_checkpoint": "siglip2-finetune-full/checkpoint-157",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 157,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9614,
+      "eval_loss": 0.11236772686243057,
+      "eval_model_preparation_time": 0.0024,
+      "eval_runtime": 61.0327,
+      "eval_samples_per_second": 81.923,
+      "eval_steps_per_second": 10.24,
+      "step": 157
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 314,
+  "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": 4.1877747910656e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-157/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60bfe4936cb8662967af80740b170b7ee49a77c617cfb4b4d72cb94fb4856548
+size 5304

checkpoint-314/config.json

@@ -0,0 +1,46 @@
+{
+  "architectures": [
+    "SiglipForImageClassification"
+  ],
+  "id2label": {
+    "0": "Female \u2640",
+    "1": "Male \u2642"
+  },
+  "initializer_factor": 1.0,
+  "label2id": {
+    "Female \u2640": 0,
+    "Male \u2642": 1
+  },
+  "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": "4.51.0.dev0",
+  "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-314/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:672245c638f4bced0d3d2c6dc3b4c8e1b936ad88259e443dfbe919a677d3bae3
+size 371567992

checkpoint-314/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca2c61bce314c08c2c635e0305545daff08656f2025c9347f009aa9877b246e3
+size 686555770

checkpoint-314/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-314/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d268ac255a6c083faad4615b0dc4cbdb3cece12ea20b61aa70a45e69eb36fdc
+size 14244

checkpoint-314/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b7714de473690f533461a318746634bcf917a385380970c1b2a5fed17283c74
+size 1064

checkpoint-314/trainer_state.json

@@ -0,0 +1,54 @@
+{
+  "best_global_step": 314,
+  "best_metric": 0.07697099447250366,
+  "best_model_checkpoint": "siglip2-finetune-full/checkpoint-314",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 314,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9614,
+      "eval_loss": 0.11236772686243057,
+      "eval_model_preparation_time": 0.0024,
+      "eval_runtime": 61.0327,
+      "eval_samples_per_second": 81.923,
+      "eval_steps_per_second": 10.24,
+      "step": 157
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.972,
+      "eval_loss": 0.07697099447250366,
+      "eval_model_preparation_time": 0.0024,
+      "eval_runtime": 60.4043,
+      "eval_samples_per_second": 82.776,
+      "eval_steps_per_second": 10.347,
+      "step": 314
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 314,
+  "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": 8.3755495821312e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-314/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60bfe4936cb8662967af80740b170b7ee49a77c617cfb4b4d72cb94fb4856548
+size 5304

config.json

@@ -0,0 +1,46 @@
+{
+  "architectures": [
+    "SiglipForImageClassification"
+  ],
+  "id2label": {
+    "0": "Female \u2640",
+    "1": "Male \u2642"
+  },
+  "initializer_factor": 1.0,
+  "label2id": {
+    "Female \u2640": 0,
+    "Male \u2642": 1
+  },
+  "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": "4.51.0.dev0",
+  "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 sha256:672245c638f4bced0d3d2c6dc3b4c8e1b936ad88259e443dfbe919a677d3bae3
+size 371567992

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 sha256:60bfe4936cb8662967af80740b170b7ee49a77c617cfb4b4d72cb94fb4856548
+size 5304