Duplicate from jaranohaal/vit-base-violence-detection

Co-authored-by: Maksat Faizuldanov <jaranohaal@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 +1,57 @@
+---
+language: en
+datasets:
+- abdulmananraja/real-life-violence-situations
+tags:
+- image-classification
+- vision
+- violence-detection
+license: apache-2.0
+---
+
+# ViT Base Violence Detection
+
+## Model Description
+
+This is a Vision Transformer (ViT) model fine-tuned for violence detection. The model is based on [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) and has been trained on the [Real Life Violence Situations](https://www.kaggle.com/datasets/mohamedmustafa/real-life-violence-situations-dataset) dataset from Kaggle to classify images into violent or non-violent categories.
+
+## Intended Use
+
+The model is intended for use in applications where detecting violent content in images is necessary. This can include:
+
+- Content moderation
+- Surveillance
+- Parental control software
+  
+## Model accuracy
+
+Test accuracy for Vit Base = 98.80%
+Loss = 0.20038144290447235
+
+## How to Use
+
+Here is an example of how to use this model for image classification:
+
+```python
+import torch
+from transformers import ViTForImageClassification, ViTFeatureExtractor
+from PIL import Image
+
+# Load the model and feature extractor
+model = ViTForImageClassification.from_pretrained('jaranohaal/vit-base-violence-detection')
+feature_extractor = ViTFeatureExtractor.from_pretrained('jaranohaal/vit-base-violence-detection')
+
+# Load an image
+image = Image.open('image.jpg')
+
+# Preprocess the image
+inputs = feature_extractor(images=image, return_tensors="pt")
+
+# Perform inference
+with torch.no_grad():
+    outputs = model(**inputs)
+    logits = outputs.logits
+    predicted_class_idx = logits.argmax(-1).item()
+
+# Print the predicted class
+print("Predicted class:", model.config.id2label[predicted_class_idx])

config.json

@@ -0,0 +1,21 @@
+{
+  "_name_or_path": "jaranohaal/vit-base-violence-detection",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "hidden_size": 768,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "image_size": 224,
+  "patch_size": 16,
+  "num_channels": 3,
+  "num_labels": 2,
+  "transformers_version": "4.41.0",
+  "torch_dtype": "float32"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9eec3237288742eb4267cb2cbbbdacba5bee889be4673215bfe40e1dbd5621a5
+size 343214896

preprocessor_config.json

@@ -0,0 +1,36 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTFeatureExtractor",
+  "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 sha256:8d5cb834bdca086c9bf1b071042f49c859675714f92800b55eebc936b37bd43e
+size 343259818