README.md

---
license: apache-2.0
library_name: litert
pipeline_tag: image-classification
tags: [nima, image-quality-assessment, aesthetic, technical, mobilenet, litert, tflite, on-device, gpu]
base_model: idealo/image-quality-assessment
---

# NIMA — LiteRT on-device image quality assessment

[NIMA (Neural Image Assessment)](https://github.com/idealo/image-quality-assessment) (idealo,
Apache-2.0) re-authored for LiteRT: score a photo's quality on a **1-10** scale. Two MobileNet
models — **aesthetic** (AVA) and **technical** (TID2013) — each predict a 10-bin score distribution;
the score is the distribution mean. Both run fully on the CompiledModel **GPU** (~6.4 MB each).

Verified on a Pixel 8a: ~173 ms for both models; tflite-vs-Keras score parity 0.999998 (aesthetic) /
0.999915 (technical).

## Files
| file | in → out | delegate |
|---|---|---|
| `nima_aesthetic_fp16.tflite` | image [1,224,224,3] → dist [10] | GPU |
| `nima_technical_fp16.tflite` | image [1,224,224,3] → dist [10] | GPU |

```
image →[resize 224² · MobileNet /127.5−1]→ [GPU MobileNet]→ softmax dist[10] →[Σ i·pᵢ]→ score 1-10
```

## Minimal usage (Python)

```python
import numpy as np
from PIL import Image
from ai_edge_litert.interpreter import Interpreter

img = Image.open("photo.jpg").convert("RGB").resize((224, 224))
x = (np.asarray(img, np.float32) / 127.5 - 1.0)[None]        # NHWC, [-1,1]

def score(model):
    it = Interpreter(model_path=model); it.allocate_tensors()
    it.set_tensor(it.get_input_details()[0]["index"], x); it.invoke()
    dist = it.get_tensor(it.get_output_details()[0]["index"])[0]
    return float((np.arange(10) + 1) @ dist)                 # mean over 1..10

print("aesthetic", score("nima_aesthetic_fp16.tflite"))
print("technical", score("nima_technical_fp16.tflite"))
```

## Minimal usage (Kotlin, LiteRT CompiledModel)

```kotlin
val m = CompiledModel.create(assets, "nima_aesthetic_fp16.tflite", CompiledModel.Options(Accelerator.GPU), null)
val inp = m.createInputBuffers(); val out = m.createOutputBuffers()
inp[0].writeFloat(preprocess(bitmap))       // resize 224², NHWC, v/127.5f - 1f
m.run(inp, out)
val dist = out[0].readFloat()               // [10]
var score = 0f; for (i in 0 until 10) score += (i + 1) * dist[i]   // 1-10
```

## Upstream

[idealo/image-quality-assessment](https://github.com/idealo/image-quality-assessment) (Apache-2.0) —
NIMA MobileNet aesthetic + technical weights. Paper: *NIMA: Neural Image Assessment* (Talebi &
Milanfar, 2018).