VGGFace Models

Overview

VGGFace is a deep convolutional neural network model designed for face recognition tasks. Based on the VGG architecture, it uses a deep structure with small convolutional filters to capture detailed facial features. Trained on a large dataset of celebrity faces, VGGFace excels in face recognition, verification, and feature extraction, making it a widely used model in both research and industry due to its high accuracy and versatility.

Model Conversion Flow

Precondition

Note

For better compatibility, it is recommended to use Python 3.7 when working with these models, as it has higher compatibility with certain libraries and frameworks.

Get Source Model

Follow these steps to set up and convert the VGGFace model using PyTorch.

1. Clone the VGGFace PyTorch Repository:

   git clone https://github.com/prlz77/vgg-face.pytorch.git
   cd vgg-face.pytorch/
   

2. Download and Extract the Pretrained VGGFace Model:

   Download the pretrained VGGFace model from the following link:

   wget https://www.robots.ox.ac.uk/~vgg/software/vgg_face/src/vgg_face_torch.tar.gz
   

   Extract the downloaded tar file:

   tar zxvf vgg_face_torch.tar.gz
   

   Move the extracted files to the pretrained directory in the cloned repository:

   mv vgg_face_torch/* pretrained/
   

3. Modify the VGGFace Model Script:

   Open the model script in a text editor:

   gedit "models/vgg_face.py"
   

   Add the following lines to trace the model and save it as a TorchScript file:

   traced_model = torch.jit.trace(model, im)
   traced_model.save("vggface_traced_model.pt")
   print("Traced model saved successfully.")
   

   After adding the code, run the modified script:

   python3 models/vgg_face.py
   

Converting Model for Deployment

Before you begin, ensure that the NeuroPilot Converter Tool is installed. If you haven’t installed it yet, please follow the instructions in the “Install and Verify NeuroPilot Converter Tool” section of the same guide.

Quant8 Conversion Process

1. Generate Calibration Data:

   The following script creates a directory named data and generates 100 batches of random input data, each saved as a .npy file. This data is used for calibration during the quantization process.

   python generate_data_batches.py
   

   import os
   import numpy as np
   
   os.mkdir('data')
   for i in range(100):
       data = np.random.randn(1, 3, 224, 224).astype(np.float32)
       np.save('data/batch_{}.npy'.format(i), data)
   

2. Convert to Quantized TFLite Format:

   Use the following command to convert the model to a quantized TFLite format using the generated calibration data:

   mtk_pytorch_converter                                 \
       --input_script_module_file=vggface_traced_model.pt    \
       --output_file=vggface_traced_model_ptq_quant.tflite   \
       --input_shapes=1,3,224,224                            \
       --quantize=True                                       \
       --input_value_ranges=-1,1                             \
       --calibration_data_dir=data/                          \
       --calibration_data_regexp=batch_.*\.npy
   

3. Convert to Quantized DLA Format

   1 Download the NeuroPilot SDK All-In-One Bundle:

   Visit the following download page and download the necessary bundle: NeuroPilot Downloads

   2. Extract the Bundle:

      After downloading, extract the bundle using the following command:

      tar zxvf neuropilot-sdk-basic-<version>.tar.gz
      

   3. Set the Environment Variables:

      Set the environment variables to point to the SDK:

      export LD_LIBRARY_PATH=/path/to/neuropilot-sdk-basic-<version>/neuron_sdk/host/lib
      

   4. Convert INT8 TFLite Model to DLA Format:

      Use the NeuroPilot Converter Tool to convert your TFLite model into the DLA format. The following example shows how to convert an INT8 TFLite model to DLA format using the specified architecture (mdla3.0):

      /path/to/neuropilot-sdk-basic-<version>/neuron_sdk/host/bin/ncc-tflite --arch=mdla3.0 vggface_traced_model_ptq_quant.tflite
      

Note

To ensure compatibility with your device, please download and use NeuroPilot SDK version 6. Other versions might not be fully supported.

FP32 Conversion Process

1. Convert to FP32 TFLite Format:

   To convert the model to a non-quantized (FP32) TFLite format, use the following command:

   mtk_pytorch_converter                                 \
       --input_script_module_file=vggface_traced_model.pt \
       --output_file=vggface_traced_model.tflite          \
       --input_shapes=1,3,224,224
   

2. Convert to FP32 DLA Format

   1. Set the Environment Variables:

      Set the environment variables to point to the SDK:

      export LD_LIBRARY_PATH=/path/to/neuropilot-sdk-basic-<version>/neuron_sdk/host/lib
      

   2. Convert FP32 TFLite Model to DLA Format:

      Use the NeuroPilot Converter Tool to convert your FP32 TFLite model into the DLA format. The following example shows how to convert an FP32 TFLite model to DLA format using the specified architecture (mdla3.0) and enabling relaxed FP32 operations:

      /path/to/neuropilot-sdk-basic-<version>/neuron_sdk/host/bin/ncc-tflite --arch=mdla3.0 --relax-fp32 vggface_traced_model.tflite
      

Model Information

Note

The models and benchmark data mentioned below have been processed using the mtk_converter.

General Information

The following table contains general information about the model. The details, such as input size, GFLOPS, and number of parameters, are sourced from the official PyTorch documentation at: VGG16 Model.

Property	Value
Category	Recognition
Input Size	224x224
#MACs (G)	None
#Params (M)	None
Training Framework	PyTorch
Inference Framework	TFLite

Pre-converted Model

Deployable Model

Model Type	Download Link	Supported Backend
Quant8 Model package	Download: Quant8	NeuronSDK
Float32 Model package	Download: Fp32	CPU,GPU,ArmNN,Neuron Stable Delegate,NeuronSDK

Model Properties

• VGGFace-quant8

Inputs

Property	Value
Name	x.1
Tensor	int8[1,3,224,224]
Identifier	10
Quantization	Linear
Quantization Range	-1.0039 ≤ 0.0078 * q ≤ 0.9961

Outputs

Property	Value
Name	238
Tensor	int8[1,2622]
Identifier	52
Quantization	Linear
Quantization Range	-0.0163 ≤ 0.0002 * (q + 30) ≤ 0.0261

• VGGFace-fp32

Inputs

Property	Value
Name	x.1
Tensor	float32[1,3,224,224]
Identifier	16

Outputs

Property	Value
Name	238
Tensor	float32[1,2622]
Identifier	46

Benchmark Results

Note

The benchmark results shown below were measured with performance mode enabled. These numbers are for reference only, as actual performance may vary depending on the hardware and platform used.

Please note the following limitations:

1. The G350 does not support Neuron Stable Delegate and NeuronSDK because the hardware does not yet support these features.

2. The model may not run on certain backends due to custom operators generated by the MTK converter. These custom operators are not recognized or supported by the TensorFlow Lite interpreter, which may lead to incompatibility issues during inference.

3. Running models on the G350 using ArmNN inference may result in a crash due to the model size being too large for the platform to handle.

• VGGFace-quant8

Run model (.tflite) 10 times	CPU (Thread:8)	GPU	ARMNN(GpuAcc)	ARMNN(CpuAcc)	Neuron Stable Delegate	NeuronSDK
G350	N/A	N/A	N/A	N/A	N/A	N/A
G510	N/A	N/A	N/A	N/A	N/A	25.04 ms
G700	N/A	N/A	N/A	N/A	N/A	17.04 ms
G1200	N/A	N/A	N/A	N/A	N/A	24.04 ms

• VGGFace-fp32

Run model (.tflite) 10 times	CPU (Thread:8)	GPU	ARMNN(GpuAcc)	ARMNN(CpuAcc)	Neuron Stable Delegate	NeuronSDK
G350	2208.66 ms (Thread:4)	853.617 ms	N/A	N/A	N/A	N/A
G510	674.378 ms	295.808 ms	222.366 ms	236.165 ms	81.971 ms	81.7 ms
G700	457.396 ms	232.558 ms	168.644 ms	193.350 ms	56.405 ms	56.04 ms
G1200	385.180 ms	133.887 ms	97.913 ms	113.238 ms	49.548 ms	49.05 ms

Run Benchmark Tools

This section will guide you on how to execute the benchmark tool with different delegates and hardware configurations.

1. First, push your TFLite model to the target device:

adb push <your_tflite_model> /usr/share/label_image/

Make sure to replace <your_tflite_model> with the actual path of your TFLite model.

2. Next, open an ADB shell to the target device:

adb shell

After this, you can execute the following commands directly from the shell.

Execute on CPU (8 threads)

To execute the benchmark on the CPU using 8 threads, run the following command:

benchmark_model --graph=/usr/share/label_image/<your_tflite_model> --num_threads=8 --num_runs=10

Execute on GPU, with GPU delegate

To execute the benchmark on the GPU using the TensorFlow Lite GPU delegate, run the following command:

benchmark_model --graph=/usr/share/label_image/<your_tflite_model> --use_gpu=1 --allow_fp16=0 --gpu_precision_loss_allowed=0 --num_runs=10

Execute on GPU, with Arm NN delegate

To execute the benchmark on the GPU using the Arm NN delegate, use the following command:

benchmark_model --graph=/usr/share/label_image/<your_tflite_model> --external_delegate_path=/usr/lib/libarmnnDelegate.so.29 --external_delegate_options="backends:GpuAcc" --num_runs=10

Execute on CPU, with Arm NN delegate

To run the benchmark on the CPU using the Arm NN delegate, use the following command:

benchmark_model --graph=/usr/share/label_image/<your_tflite_model> --external_delegate_path=/usr/lib/libarmnnDelegate.so.29 --external_delegate_options="backends:CpuAcc" --num_runs=10

Execute on APU, with Neuron Delegate

For executing on the APU using the Neuron delegate, run the following command:

benchmark_model --stable_delegate_settings_file=/usr/share/label_image/stable_delegate_settings.json --use_nnapi=false --use_xnnpack=false --use_gpu=false --min_secs=20 --graph=/usr/share/label_image/<your_tflite_model>

Note

If you are using the G350 platform, please make the following adjustments:

• For CPU-based benchmarks, change the –num_threads parameter to 4:

  benchmark_model --graph=/usr/share/label_image/<your_tflite_model> --num_threads=4 --use_xnnpack=0 --num_runs=10
  

• For all benchmarks (CPU, GPU, Arm NN), add the parameter –use_xnnpack=0 to disable the XNNPACK delegate

Neuron SDK

Follow these steps to benchmark your TensorFlow Lite model using the Neuron SDK with MDLA 3.0:

1. Transfer the Model to the Device:

   Use adb to push your TFLite model to the device:

   adb push <your_tflite_model> /user/share/benchmark_dla/
   

2. Access the Device Shell:

   Connect to your device’s shell:

   adb shell
   

3. Navigate to the Benchmark Directory:

   Change to the directory where the model is stored:

   cd /user/share/benchmark_dla/
   

4. Run the Benchmark:

   Execute the benchmarking script with the following command:

   python3 benchmark.py --file <your_tflite_model> --target mdla3.0 --profile --options='--relax-fp32'
   

Description:

• The benchmark.py script runs a performance evaluation on your model using MDLA 3.0.

• The –file parameter specifies the path to your TFLite model.

• The –target mdla3.0 option sets the target hardware to MDLA 3.0.

• The –profile flag enables profiling to provide detailed performance metrics.

• The –options=’–relax-fp32’ option allows relaxation of floating-point precision to improve compatibility with MDLA.

Note

Troubleshooting:

If you encounter the following error:

subprocess.CalledProcessError: Command 'ncc-tflite -arch mdla3.0 vggface_traced_model_ptq_quant.tflite -o vggface_traced_model_ptq_quant-mdla3.0.dla --relax-fp32' returned non-zero exit status

Resolve the issue with these steps:

1. Push the `.dla` file to your device:

   adb push vggface_traced_model_ptq_quant.dla /user/share/benchmark_dla/
   

2. Access the device shell:

   adb shell
   

3. Navigate to the directory:

   cd /user/share/benchmark_dla/
   

4. Rename the `.dla` file:

   mv vggface_traced_model_ptq_quant.dla vggface_traced_model_ptq_quant-mdla3.0.dla
   

5. Re-run the benchmark script:

   python3 benchmark.py --file vggface_traced_model_ptq_quant.tflite --target mdla3.0 --profile --options='--relax-fp32'