Terjemahan disediakan oleh mesin penerjemah. Jika konten terjemahan yang diberikan bertentangan dengan versi bahasa Inggris aslinya, utamakan versi bahasa Inggris.

# Kerangka Kerja, Perangkat, Sistem, dan Arsitektur yang Didukung
<a name="neo-supported-devices-edge"></a>

Amazon SageMaker Neo mendukung kerangka kerja pembelajaran mesin umum, perangkat edge, sistem operasi, dan arsitektur chip. Cari tahu apakah Neo mendukung kerangka kerja, perangkat tepi, OS, dan arsitektur chip Anda dengan memilih salah satu topik di bawah ini.

Anda dapat menemukan daftar model yang telah diuji oleh Tim Amazon SageMaker Neo di [Model yang Diuji](neo-supported-edge-tested-models.md) bagian tersebut.

**catatan**  
Perangkat Ambarella memerlukan file tambahan untuk dimasukkan dalam file TAR terkompresi sebelum dikirim untuk kompilasi. Untuk informasi selengkapnya, lihat [Memecahkan Masalah Kesalahan Ambarella](neo-troubleshooting-target-devices-ambarella.md).
TIM-VX (libtim-vx.so) diperlukan untuk i.MX 8M Plus. [Untuk informasi tentang cara membangun TIM-VX, lihat repositori TIM-VX. GitHub ](https://github.com/VeriSilicon/TIM-VX)

**Topics**
+ [Kerangka Kerja yang Didukung](neo-supported-devices-edge-frameworks.md)
+ [Perangkat, Arsitektur Chip, dan Sistem yang Didukung](neo-supported-devices-edge-devices.md)
+ [Model yang Diuji](neo-supported-edge-tested-models.md)

# Kerangka Kerja yang Didukung
<a name="neo-supported-devices-edge-frameworks"></a>

Amazon SageMaker Neo mendukung kerangka kerja berikut. 


| Kerangka Kerja | Versi Kerangka | Versi Model | Model | Format Model (dikemas dalam\$1.tar.gz) | Toolkit | 
| --- | --- | --- | --- | --- | --- | 
| MXNet | 1.8 | Mendukung 1,8 atau sebelumnya | Klasifikasi Gambar, Deteksi Objek, Segmentasi Semantik, Estimasi Pose, Pengenalan Aktivitas | Satu file simbol (.json) dan satu file parameter (.params) | GluonCV v0.8.0 | 
| ONNX | 1.7 | Mendukung 1.7 atau sebelumnya | Klasifikasi Gambar, SVM | Satu file model (.onnx) |  | 
| Keras | 2.2 | Mendukung 2.2 atau sebelumnya | Klasifikasi Gambar | Satu file definisi model (.h5) |  | 
| PyTorch | 1.7, 1.8 | Mendukung 1.7, 1.8 atau sebelumnya | Klasifikasi Gambar, Deteksi Objek | Satu file definisi model (.pth) |  | 
| TensorFlow | 1.15, 2.4, 2.5 (hanya untuk instance ml.inf1.\$1) | Mendukung 1.15, 2.4, 2.5 (hanya untuk instance ml.inf1.\$1) atau sebelumnya | Klasifikasi Gambar, Deteksi Objek | \$1Untuk model yang disimpan, satu file.pb atau satu file.pbtxt dan direktori variabel yang berisi variabel\$1Untuk model beku, hanya satu file.pb atau .pbtxt |  | 
| TensorFlow-Ringan | 1.15 | Mendukung 1,15 atau sebelumnya | Klasifikasi Gambar, Deteksi Objek | File flatbuffer definisi satu model (.tflite) |  | 
| XGBoost | 1.3 | Mendukung 1.3 atau sebelumnya | Pohon Keputusan | Satu file XGBoost model (.model) di mana jumlah node dalam pohon kurang dari 2 ^ 31 |  | 
| DARKNET |  |  | Klasifikasi Gambar, Deteksi Objek (model Yolo tidak didukung) | Satu file konfigurasi (.cfg) dan satu file bobot (.weights) |  | 

# Perangkat, Arsitektur Chip, dan Sistem yang Didukung
<a name="neo-supported-devices-edge-devices"></a>

Amazon SageMaker Neo mendukung perangkat, arsitektur chip, dan sistem operasi berikut.

## Perangkat
<a name="neo-supported-edge-devices"></a>

Anda dapat memilih perangkat menggunakan daftar tarik-turun di [konsol Amazon SageMaker AI](https://console.aws.amazon.com/sagemaker) atau dengan menentukan `TargetDevice` konfigurasi output API. [https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateCompilationJob.html](https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateCompilationJob.html)

Anda dapat memilih dari salah satu perangkat edge berikut: 


| Daftar Perangkat | Sistem pada Chip (SoC) | Sistem Operasi | Arsitektur | Akselerator | Contoh Opsi Kompiler | 
| --- | --- | --- | --- | --- | --- | 
| lorong | Tidak ada | Linux | ARM64 | Mali | Tidak ada | 
| amba\$1cv2 | CV2 | Arch Linux | ARM64 | cvflow | Tidak ada | 
| amba\$1cv22 | CV22 | Arch Linux | ARM64 | cvflow | Tidak ada | 
| amba\$1cv25 | CV25 | Arch Linux | ARM64 | cvflow | Tidak ada | 
| corel | Tidak ada | iOS, macOS | Tidak ada | Tidak ada | \$1"class\$1labels": "imagenet\$1labels\$11000.txt"\$1 | 
| imx8qm | NXP imx8 | Linux | ARM64 | Tidak ada | Tidak ada | 
| imx8mplus | i.MX 8M Plus | Linux | ARM64 | NPU | Tidak ada | 
| jacinto\$1tda4vm | TDA4VM | Linux | LENGAN | TDA4VM | Tidak ada | 
| jetson\$1nano | Tidak ada | Linux | ARM64 | NVIDIA | \$1'gpu-code': 'sm\$153', 'trt-ver': '5.0.6', 'cuda-ver': '10.0'\$1Untuk`TensorFlow2`, `{'JETPACK_VERSION': '4.6', 'gpu_code': 'sm_72'}` | 
| jetson\$1tx1 | Tidak ada | Linux | ARM64 | NVIDIA | \$1'gpu-code': 'sm\$153', 'trt-ver': '6.0.1', 'cuda-ver': '10.0'\$1 | 
| jetson\$1tx2 | Tidak ada | Linux | ARM64 | NVIDIA | \$1'gpu-code': 'sm\$162', 'trt-ver': '6.0.1', 'cuda-ver': '10.0'\$1 | 
| jetson\$1xavier | Tidak ada | Linux | ARM64 | NVIDIA | \$1'gpu-code': 'sm\$172', 'trt-ver': '5.1.6', 'cuda-ver': '10.0'\$1 | 
| qcs605 | Tidak ada | Android | ARM64 | Mali | \$1'ANDROID\$1PLATFORM': 27\$1 | 
| qcs603 | Tidak ada | Android | ARM64 | Mali | \$1'ANDROID\$1PLATFORM': 27\$1 | 
| rasp3b | LENGAN A56 | Linux | ARM\$1EABIHF | Tidak ada | \$1'mattr': ['\$1neon']\$1 | 
| rasp4b | LENGAN A72 | Tidak ada | Tidak ada | Tidak ada | Tidak ada | 
| rk3288 | Tidak ada | Linux | ARM\$1EABIHF | Mali | Tidak ada | 
| rk3399 | Tidak ada | Linux | ARM64 | Mali | Tidak ada | 
| sbe\$1c | Tidak ada | Linux | x86\$164 | Tidak ada | \$1'mcpu': 'core-avx2'\$1 | 
| sitara\$1am57x | AM57X | Linux | ARM64 | EVE dan/atau C66x DSP | Tidak ada | 
| x86\$1win32 | Tidak ada | Windows 10 | X86\$132 | Tidak ada | Tidak ada | 
| x86\$1win64 | Tidak ada | Windows 10 | X86\$132 | Tidak ada | Tidak ada | 

[Untuk informasi selengkapnya tentang opsi kompiler nilai kunci JSON untuk setiap perangkat target, lihat `CompilerOptions` bidang dalam tipe data API. `OutputConfig`](https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html)

## Sistem dan Arsitektur Chip
<a name="neo-supported-edge-granular"></a>

Tabel pencarian berikut memberikan informasi mengenai sistem operasi dan arsitektur yang tersedia untuk pekerjaan kompilasi model Neo. 

------
#### [ Linux ]


| Akselerator | X86\$164 | X86 | ARM64 | ARM\$1EABIHF | ARM\$1EABI | 
| --- | --- | --- | --- | --- | --- | 
| Tidak ada akselerator (CPU) | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/success_icon.svg) Ya | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/negative_icon.svg) Tidak | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/success_icon.svg) Ya | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/success_icon.svg) Ya | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/success_icon.svg) Ya | 
| GPU Nvidia | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/success_icon.svg) Ya | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/negative_icon.svg) Tidak | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/success_icon.svg) Ya | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/negative_icon.svg) Tidak | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/negative_icon.svg) Tidak | 
| Intel\$1Grafis | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/success_icon.svg) Ya | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/negative_icon.svg) Tidak | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/negative_icon.svg) Tidak | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/negative_icon.svg) Tidak | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/negative_icon.svg) Tidak | 
| ARM Mali | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/negative_icon.svg) Tidak | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/negative_icon.svg) Tidak | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/success_icon.svg) Ya | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/success_icon.svg) Ya | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/success_icon.svg) Ya | 

------
#### [ Android ]


| Akselerator | X86\$164 | X86 | ARM64 | ARM\$1EABIHF | ARM\$1EABI | 
| --- | --- | --- | --- | --- | --- | 
| Tidak ada akselerator (CPU) | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/success_icon.svg) Ya | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/success_icon.svg) Ya | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/success_icon.svg) Ya | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/negative_icon.svg) Tidak | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/success_icon.svg) Ya | 
| GPU Nvidia | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/negative_icon.svg) Tidak | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/negative_icon.svg) Tidak | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/negative_icon.svg) Tidak | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/negative_icon.svg) Tidak | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/negative_icon.svg) Tidak | 
| Intel\$1Grafis | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/success_icon.svg) Ya | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/success_icon.svg) Ya | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/negative_icon.svg) Tidak | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/negative_icon.svg) Tidak | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/negative_icon.svg) Tidak | 
| ARM Mali | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/negative_icon.svg) Tidak | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/negative_icon.svg) Tidak | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/success_icon.svg) Ya | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/negative_icon.svg) Tidak | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/success_icon.svg) Ya | 

------
#### [ Windows ]


| Akselerator | X86\$164 | X86 | ARM64 | ARM\$1EABIHF | ARM\$1EABI | 
| --- | --- | --- | --- | --- | --- | 
| Tidak ada akselerator (CPU) | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/success_icon.svg) Ya | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/success_icon.svg) Ya | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/negative_icon.svg) Tidak | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/negative_icon.svg) Tidak | ![\[alt text not found\]](http://docs.aws.amazon.com/id_id/sagemaker/latest/dg/images/negative_icon.svg) Tidak | 

------

# Model yang Diuji
<a name="neo-supported-edge-tested-models"></a>

Bagian yang dapat dilipat berikut memberikan informasi tentang model pembelajaran mesin yang diuji oleh tim Amazon SageMaker Neo. Perluas bagian yang dapat dilipat berdasarkan kerangka kerja Anda untuk memeriksa apakah model telah diuji.

**catatan**  
Ini bukan daftar lengkap model yang dapat dikompilasi dengan Neo.

Lihat [Kerangka Kerja yang Didukung](neo-supported-devices-edge-frameworks.md) dan [Operator yang Didukung SageMaker AI Neo](https://aws.amazon.com/releasenotes/sagemaker-neo-supported-frameworks-and-operators/) untuk mengetahui apakah Anda dapat mengkompilasi model Anda dengan SageMaker Neo.

## DarkNet
<a name="collapsible-section-01"></a>


| Model | LENGAN V8 | ARM Mali | Ambarella CV22 | Nvidia | Panorama | TI TDA4 VM | Qualcomm 03 QCS6 | X86\$1Linux | X86\$1Windows | 
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | 
| Alexnet |  |  |  |  |  |  |  |  |  | 
| Resnet50 | X | X |  | X | X | X |  | X | X | 
| YOLOv2 |  |  |  | X | X | X |  | X | X | 
| YOLOv2\$1kecil | X | X |  | X | X | X |  | X | X | 
| YOLOv3\$1416 |  |  |  | X | X | X |  | X | X | 
| YOLOv3\$1kecil | X | X |  | X | X | X |  | X | X | 

## MXNet
<a name="collapsible-section-02"></a>


| Model | LENGAN V8 | ARM Mali | Ambarella CV22 | Nvidia | Panorama | TI TDA4 VM | Qualcomm 03 QCS6 | X86\$1Linux | X86\$1Windows | 
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | 
| Alexnet |  |  | X |  |  |  |  |  |  | 
| Densenet121 |  |  | X |  |  |  |  |  |  | 
| DenseNet201 | X | X | X | X | X | X |  | X | X | 
| GoogLeNet | X | X |  | X | X | X |  | X | X | 
| InceptionV3 |  |  |  | X | X | X |  | X | X | 
| MobileNet0,75 | X | X |  | X | X | X |  |  | X | 
| MobileNet1.0 | X | X | X | X | X | X |  |  | X | 
| MobileNetV2\$10.5 | X | X |  | X | X | X |  |  | X | 
| MobileNetV2\$11.0 | X | X | X | X | X | X | X | X | X | 
| MobileNetV3\$1Besar | X | X | X | X | X | X | X | X | X | 
| MobileNetV3\$1Kecil | X | X | X | X | X | X | X | X | X | 
| ResNeSt50 |  |  |  | X | X |  |  | X | X | 
| ResNet18\$1v1 | X | X | X | X | X | X |  |  | X | 
| ResNet18\$1v2 | X | X |  | X | X | X |  |  | X | 
| ResNet50\$1v1 | X | X | X | X | X | X |  | X | X | 
| ResNet50\$1v2 | X | X | X | X | X | X |  | X | X | 
| ResNext101\$132x4d |  |  |  |  |  |  |  |  |  | 
| ResNext50\$132x4d | X |  | X | X | X |  |  | X | X | 
| SENet\$1154 |  |  |  | X | X | X |  | X | X | 
| SE\$1 50\$132x4d ResNext | X | X |  | X | X | X |  | X | X | 
| SqueezeNet1.0 | X | X | X | X | X | X |  |  | X | 
| SqueezeNet1.1 | X | X | X | X | X | X |  | X | X | 
| VGG11 | X | X | X | X | X |  |  | X | X | 
| Xception | X | X | X | X | X | X |  | X | X | 
| darknet53 | X | X |  | X | X | X |  | X | X | 
| resnet18\$1v1b\$10.89 | X | X |  | X | X | X |  |  | X | 
| resnet50\$1v1d\$10.11 | X | X |  | X | X | X |  |  | X | 
| resnet50\$1v1d\$10.86 | X | X | X | X | X | X |  | X | X | 
| ssd\$1512\$1mobilenet1.0\$1coco | X |  | X | X | X | X |  | X | X | 
| ssd\$1512\$1mobilenet1.0\$1voc | X |  | X | X | X | X |  | X | X | 
| ssd\$1resnet50\$1v1 | X |  | X | X | X |  |  | X | X | 
| yolo3\$1darknet53\$1coco | X |  |  | X | X |  |  | X | X | 
| yolo3\$1mobilenet1.0\$1coco | X | X |  | X | X | X |  | X | X | 
| deeplab\$1resnet50 |  |  | X |  |  |  |  |  |  | 

## Keras
<a name="collapsible-section-03"></a>


| Model | LENGAN V8 | ARM Mali | Ambarella CV22 | Nvidia | Panorama | TI TDA4 VM | Qualcomm 03 QCS6 | X86\$1Linux | X86\$1Windows | 
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | 
| densenet121 | X | X | X | X | X | X |  | X | X | 
| densenet201 | X | X | X | X | X | X |  |  | X | 
| inception\$1v3 | X | X |  | X | X | X |  | X | X | 
| mobilenet\$1v1 | X | X | X | X | X | X |  | X | X | 
| mobilenet\$1v2 | X | X | X | X | X | X |  | X | X | 
| resnet152\$1v1 |  |  |  | X | X |  |  |  | X | 
| resnet152\$1v2 |  |  |  | X | X |  |  |  | X | 
| resnet50\$1v1 | X | X | X | X | X |  |  | X | X | 
| resnet50\$1v2 | X | X | X | X | X | X |  | X | X | 
| vgg16 |  |  | X | X | X |  |  | X | X | 

## ONNX
<a name="collapsible-section-04"></a>


| Model | LENGAN V8 | ARM Mali | Ambarella CV22 | Nvidia | Panorama | TI TDA4 VM | Qualcomm 03 QCS6 | X86\$1Linux | X86\$1Windows | 
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | 
| alexnet |  |  | X |  |  |  |  |  |  | 
| mobilenetv2-1.0 | X | X | X | X | X | X |  | X | X | 
| resnet18v1 | X |  |  | X | X |  |  |  | X | 
| resnet18v2 | X |  |  | X | X |  |  |  | X | 
| resnet50v1 | X |  | X | X | X |  |  | X | X | 
| resnet50v2 | X |  | X | X | X |  |  | X | X | 
| resnet152v1 |  |  |  | X | X | X |  |  | X | 
| resnet152v2 |  |  |  | X | X | X |  |  | X | 
| squeezenet1.1 | X |  | X | X | X | X |  | X | X | 
| vgg19 |  |  | X |  |  |  |  |  | X | 

## PyTorch (FP32)
<a name="collapsible-section-05"></a>


| Model | LENGAN V8 | ARM Mali | Ambarella CV22 | Ambarella CV25 | Nvidia | Panorama | TI TDA4 VM | Qualcomm 03 QCS6 | X86\$1Linux | X86\$1Windows | 
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | 
| densenet121 | X | X | X | X | X | X | X |  | X | X | 
| inception\$1v3 |  | X |  |  | X | X | X |  | X | X | 
| resnet152 |  |  |  |  | X | X | X |  |  | X | 
| resnet18 | X | X |  |  | X | X | X |  |  | X | 
| resnet50 | X | X | X | X | X | X |  |  | X | X | 
| squeezenet1.0 | X | X |  |  | X | X | X |  |  | X | 
| squeezenet1.1 | X | X | X | X | X | X | X |  | X | X | 
| yolov4 |  |  |  |  | X | X |  |  |  |  | 
| yolov5 |  |  |  | X | X | X |  |  |  |  | 
| fasterrcnn\$1resnet50\$1fpn |  |  |  |  | X | X |  |  |  |  | 
| maskrcnn\$1resnet50\$1fpn |  |  |  |  | X | X |  |  |  |  | 

## TensorFlow
<a name="collapsible-section-06"></a>

------
#### [ TensorFlow ]


| Model | LENGAN V8 | ARM Mali | Ambarella CV22 | Ambarella CV25 | Nvidia | Panorama | TI TDA4 VM | Qualcomm 03 QCS6 | X86\$1Linux | X86\$1Windows | 
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | 
| densenet201 | X | X | X | X | X | X | X |  | X | X | 
| inception\$1v3 | X | X | X |  | X | X | X |  | X | X | 
| mobilenet100\$1v1 | X | X | X |  | X | X | X |  |  | X | 
| mobilenet100\$1v2.0 | X | X | X |  | X | X | X |  | X | X | 
| mobilenet130\$1v2 | X | X |  |  | X | X | X |  |  | X | 
| mobilenet140\$1v2 | X | X | X |  | X | X | X |  | X | X | 
| resnet50\$1v1.5 | X | X |  |  | X | X | X |  | X | X | 
| resnet50\$1v2 | X | X | X | X | X | X | X |  | X | X | 
| meremas | X | X | X | X | X | X | X |  | X | X | 
| topeng\$1rcnn\$1inception\$1resnet\$1v2 |  |  |  |  | X |  |  |  |  |  | 
| ssd\$1mobilenet\$1v2 |  |  |  |  | X | X |  |  |  |  | 
| lebih cepat\$1rcnn\$1resnet50\$1lowproposal |  |  |  |  | X |  |  |  |  |  | 
| rfcn\$1resnet101 |  |  |  |  | X |  |  |  |  |  | 

------
#### [ TensorFlow.Keras ]


| Model | LENGAN V8 | ARM Mali | Ambarella CV22 | Nvidia | Panorama | TI TDA4 VM | Qualcomm 03 QCS6 | X86\$1Linux | X86\$1Windows | 
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | 
| DenseNet121  | X | X |  | X | X | X |  | X | X | 
| DenseNet201 | X | X |  | X | X | X |  |  | X | 
| InceptionV3 | X | X |  | X | X | X |  | X | X | 
| MobileNet | X | X |  | X | X | X |  | X | X | 
| MobileNetv2 | X | X |  | X | X | X |  | X | X | 
| NASNetBesar |  |  |  | X | X |  |  | X | X | 
| NASNetPonsel | X | X |  | X | X | X |  | X | X | 
| ResNet101 |  |  |  | X | X | X |  |  | X | 
| ResNet101V2 |  |  |  | X | X | X |  |  | X | 
| ResNet152 |  |  |  | X | X |  |  |  | X | 
| ResNet152v2 |  |  |  | X | X |  |  |  | X | 
| ResNet50 | X | X |  | X | X |  |  | X | X | 
| ResNet50V2 | X | X |  | X | X | X |  | X | X | 
| VGG16 |  |  |  | X | X |  |  | X | X | 
| Xception | X | X |  | X | X | X |  | X | X | 

------

## TensorFlow-Ringan
<a name="collapsible-section-07"></a>

------
#### [ TensorFlow-Lite (FP32) ]


| Model | LENGAN V8 | ARM Mali | Ambarella CV22 | Nvidia | Panorama | TI TDA4 VM | Qualcomm 03 QCS6 | X86\$1Linux | X86\$1Windows | i.MX 8M Plus | 
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | 
| densenet\$12018\$104\$127 | X |  |  | X | X | X |  |  | X |  | 
| inception\$1resnet\$1v2\$12018\$104\$127 |  |  |  | X | X | X |  |  | X |  | 
| inception\$1v3\$12018\$104\$127 |  |  |  | X | X | X |  |  | X | X | 
| inception\$1v4\$12018\$104\$127 |  |  |  | X | X | X |  |  | X | X | 
| mnasnet\$10.5\$1224\$109\$107\$12018 | X |  |  | X | X | X |  |  | X |  | 
| mnasnet\$11.0\$1224\$109\$107\$12018 | X |  |  | X | X | X |  |  | X |  | 
| mnasnet\$11.3\$1224\$109\$107\$12018 | X |  |  | X | X | X |  |  | X |  | 
| mobilenet\$1v1\$10.25\$1128 | X |  |  | X | X | X |  |  | X | X | 
| mobilenet\$1v1\$10.25\$1224 | X |  |  | X | X | X |  |  | X | X | 
| mobilenet\$1v1\$10.5\$1128 | X |  |  | X | X | X |  |  | X | X | 
| mobilenet\$1v1\$10.5\$1224 | X |  |  | X | X | X |  |  | X | X | 
| mobilenet\$1v1\$10.75\$1128 | X |  |  | X | X | X |  |  | X | X | 
| mobilenet\$1v1\$10.75\$1224 | X |  |  | X | X | X |  |  | X | X | 
| mobilenet\$1v1\$11.0\$1128 | X |  |  | X | X | X |  |  | X | X | 
| mobilenet\$1v1\$11.0\$1192 | X |  |  | X | X | X |  |  | X | X | 
| mobilenet\$1v2\$11.0\$1224 | X |  |  | X | X | X |  |  | X | X | 
| resnet\$1v2\$1101 |  |  |  | X | X | X |  |  | X |  | 
| squeezenet\$12018\$104\$127 | X |  |  | X | X | X |  |  | X |  | 

------
#### [ TensorFlow-Lite (INT8) ]


| Model | LENGAN V8 | ARM Mali | Ambarella CV22 | Nvidia | Panorama | TI TDA4 VM | Qualcomm 03 QCS6 | X86\$1Linux | X86\$1Windows | i.MX 8M Plus | 
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | 
| inception\$1v1 |  |  |  |  |  |  | X |  |  | X | 
| inception\$1v2 |  |  |  |  |  |  | X |  |  | X | 
| inception\$1v3 | X |  |  |  |  | X | X |  | X | X | 
| inception\$1v4\$1299 | X |  |  |  |  | X | X |  | X | X | 
| mobilenet\$1v1\$10.25\$1128 | X |  |  |  |  | X |  |  | X | X | 
| mobilenet\$1v1\$10.25\$1224 | X |  |  |  |  | X |  |  | X | X | 
| mobilenet\$1v1\$10.5\$1128 | X |  |  |  |  | X |  |  | X | X | 
| mobilenet\$1v1\$10.5\$1224 | X |  |  |  |  | X |  |  | X | X | 
| mobilenet\$1v1\$10.75\$1128 | X |  |  |  |  | X |  |  | X | X | 
| mobilenet\$1v1\$10.75\$1224 | X |  |  |  |  | X | X |  | X | X | 
| mobilenet\$1v1\$11.0\$1128 | X |  |  |  |  | X |  |  | X | X | 
| mobilenet\$1v1\$11.0\$1224 | X |  |  |  |  | X | X |  | X | X | 
| mobilenet\$1v2\$11.0\$1224 | X |  |  |  |  | X | X |  | X | X | 
| deeplab-v3\$1513 |  |  |  |  |  |  | X |  |  |  | 

------