YOLOX_s Models

Overview

YOLOX is an anchor-free evolution of the YOLO model, designed to offer a streamlined architecture while delivering enhanced performance. It aims to bridge advancements in research with practical applications in the industry.

Getting Started

Follow these steps to set up, download, and convert the YOLOX-S model using PyTorch.

  1. Clone the YOLOX Repository:

    Clone the YOLOX repository from GitHub:

    git clone https://github.com/Megvii-BaseDetection/YOLOX.git

  2. Download the YOLOX-S PyTorch Model:

    Download the pretrained YOLOX-S model from the following command:

    cd YOLOX
wget https://github.com/Megvii-BaseDetection/YOLOX/releases/download/0.1.1rc0/yolox_s.pth

  3. Export the YOLOX-S Model to TorchScript:

    Run the export script to convert the YOLOX-S model to TorchScript format:

    python3.8 tools/export_torchscript.py -n yolox_s -c yolox_s.pth

How it Works ?

Before you begin, ensure that the NeuroPilot Converter Tool is installed.

Quant8 Conversion Process

The following script demonstrates how to convert the YOLOX model to a quantized TFLite format using the NeuroPilot Converter Tool:

  • Data Generation: A generator function creates random input data, which is used for calibration during the quantization process.

  • Model Loading: The YOLOX model is loaded from a TorchScript file.

  • Quantization: The model is set up for quantization, specifying input value ranges and using the generated calibration data.

  • Conversion: The quantized model is converted to TFLite format and saved as yolox_s_quant.tflite.

import mtk_converter
import numpy as np

def data_gen():
    for i in range(100):
        yield [np.random.randn(1, 3, 640, 640).astype(np.float32)]

converter = mtk_converter.PyTorchConverter.from_script_module_file(
    'yolox.torchscript.pt',  [[1, 3, 640, 640]],
)
converter.quantize = True
converter.input_value_ranges = [(-1.0, 1.0)]
converter.calibration_data_gen = data_gen
_ = converter.convert_to_tflite(output_file='yolox_s_quant.tflite')

FP32 Conversion Process

The following script demonstrates how to convert the YOLOX model to a non-quantized (FP32) TFLite format:

  • Data Generation: As in the quantization process, a generator function creates random input data for the conversion.

  • Model Loading: The YOLOX model is loaded from a TorchScript file.

  • Conversion: The model is converted to TFLite format without applying quantization, and the output is saved as yolox_s.tflite.

import mtk_converter
import numpy as np

def data_gen():
    for i in range(100):
        yield [np.random.randn(1, 3, 640, 640).astype(np.float32)]

converter = mtk_converter.PyTorchConverter.from_script_module_file(
    'yolox.torchscript.pt',  [[1, 3, 640, 640]],
)
converter.input_value_ranges = [(-1.0, 1.0)]
converter.calibration_data_gen = data_gen
_ = converter.convert_to_tflite(output_file='yolox_s.tflite')

Model Details

General Information

Property

Value

Category

Classification

Input Size

640x640

FLOPs (G)

26.8

#Params (M)

9.0

Training Framework

PyTorch

Inference Framework

TFLite

Quant8 Model package

Download

Float32 Model package

Download

Model Properties

Quant8

  • Format: TensorFlow Lite v3

  • Description: Exported by NeuroPilot converter v7.14.1+release

Inputs

Property

Value

Name

x.2

Tensor

int8[1,3,640,640]

Identifier

318

Quantization

Linear

Quantization Range

-1.0039 ≤ 0.0078 * q ≤ 0.9961

Outputs

Property

Value

Name

1360

Tensor

int8[1,8400,85]

Identifier

98

Quantization

Linear

Quantization Range

-2.1799 ≤ 0.0227 * (q + 32) ≤ 3.6106

Fp32

  • Format: TensorFlow Lite v3

  • Description: Exported by NeuroPilot converter v7.14.1+release

Inputs

Property

Value

Name

x.2

Tensor

float32[1,3,640,640]

Identifier

111

Outputs

Property

Value

Name

1360

Tensor

float32[1,8400,85]

Identifier

53

Performance Benchmarks

YOLOX_s-quant8

Run model (.tflite) 10 times

CPU (Thread:8)

GPU

ARMNN(GpuAcc)

ARMNN(CpuAcc)

Neuron Stable Delegate(APU)

APU(MDLA)

APU(VPU)

G350

976.244 ms (Thread:4)

1160.05 ms

703.429 ms

694.960 ms

N/A

N/A

106683 ms

G510

378.448 ms

386.428 ms

217.080 ms

174.013 ms

N/A

22.31 ms

N/A

G700

165.861 ms

265.292 ms

150.151 ms

157.308 ms

14.723 ms

15.04 ms

N/A

G1200

159.647 ms

179.024 ms

98.150 ms

87.183 ms

24.276 ms

25.05 ms

N/A

YOLOX_s-fp32

Run model (.tflite) 10 times

CPU (Thread:8)

GPU

ARMNN(GpuAcc)

ARMNN(CpuAcc)

Neuron Stable Delegate(APU)

APU(MDLA)

APU(VPU)

G350

2027.11 ms (Thread:4)

1121.93 ms

1046.59 ms

N/A

N/A

N/A

7066.75 ms

G510

821.662 ms

358.816 ms

341.251 ms

424.459 ms

69.916 ms

62.12 ms

N/A

G700

423.192 ms

248.299 ms

234.901 ms

358.942 ms

51.868 ms

44.04 ms

N/A

G1200

395.406 ms

161.877 ms

150.498 ms

205.845 ms

57.381 ms

48.05 ms

N/A

  • Widespread: CPU only, light workload.

  • Performance: CPU and GPU, medium workload.

  • Ultimate: CPU, GPU, and APUs, heavy workload.

Resources

To preview related documentation about YOLOX, please visit the Github repository