> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/shubham0204/OnDevice-Face-Recognition-Android/llms.txt
> Use this file to discover all available pages before exploring further.

# Choosing a FaceNet model

> Select between 128-dimensional and 512-dimensional FaceNet models for face embedding

FaceNet Android supports two different FaceNet models that produce embeddings of different dimensions. The choice between them impacts accuracy, performance, and storage requirements.

## Available models

The app includes two FaceNet models in the `assets` folder:

* `facenet.tflite` - Outputs 128-dimensional embeddings
* `facenet_512.tflite` - Outputs 512-dimensional embeddings

Both models accept 160×160 pixel face images as input and produce embeddings that capture unique facial features.

<Tip>
  The 512-dimensional model generally provides better accuracy for face recognition, especially with larger datasets, but requires more storage and slightly longer processing time.
</Tip>

## Switching between models

To change the FaceNet model, you need to update two files: `FaceNet.kt` and `DataModels.kt`.

### Step 1: Update the model path

In `FaceNet.kt:62`, modify the model file path:

```kotlin FaceNet.kt theme={null}
// For 128-dimensional embeddings
interpreter = Interpreter(
    FileUtil.loadMappedFile(context, "facenet.tflite"), 
    interpreterOptions
)

// For 512-dimensional embeddings
interpreter = Interpreter(
    FileUtil.loadMappedFile(context, "facenet_512.tflite"), 
    interpreterOptions
)
```

### Step 2: Update the embedding dimension

In `FaceNet.kt:34`, change the `embeddingDim` value:

```kotlin FaceNet.kt theme={null}
// For facenet.tflite
private val embeddingDim = 128

// For facenet_512.tflite
private val embeddingDim = 512
```

### Step 3: Update the database schema

In `DataModels.kt:18-21`, update the `@HnswIndex` dimensions:

```kotlin DataModels.kt theme={null}
@Entity
data class FaceImageRecord(
    @Id var recordID: Long = 0,
    @Index var personID: Long = 0,
    var personName: String = "",
    // Update dimensions to match your chosen model
    @HnswIndex(
        dimensions = 512,  // Change to 128 for facenet.tflite
        distanceType = VectorDistanceType.COSINE,
    ) var faceEmbedding: FloatArray = floatArrayOf(),
)
```

<Warning>
  Changing the embedding dimension requires rebuilding the app and clearing existing data. The ObjectBox database schema will change, and existing face records will be incompatible.
</Warning>

## Performance comparison

| Model               | Embedding Size | Accuracy | Inference Time | Storage per Face |
| ------------------- | -------------- | -------- | -------------- | ---------------- |
| facenet.tflite      | 128-dim        | Good     | \~40-60ms      | 512 bytes        |
| facenet\_512.tflite | 512-dim        | Better   | \~50-70ms      | 2048 bytes       |

<Tip>
  For most use cases with moderate dataset sizes (under 1000 faces), the 512-dimensional model provides the best balance of accuracy and performance.
</Tip>

## Model source

Both models are sourced from the [deepface](https://github.com/serengil/deepface) library and converted to TensorFlow Lite format with FP16 optimization. See the source README for conversion scripts.