Low-Precision 8-bit Integer Inference¶
Disclaimer¶
Low-precision 8-bit inference is optimized for:
Intel® architecture processors with the following instruction set architecture extensions:
Intel® Advanced Vector Extensions 512 Vector Neural Network Instructions (Intel® AVX-512 VNNI)
Intel® Advanced Vector Extensions 512 (Intel® AVX-512)
Intel® Advanced Vector Extensions 2.0 (Intel® AVX2)
Intel® Streaming SIMD Extensions 4.2 (Intel® SSE4.2)
Intel® processor graphics:
Intel® Iris® Xe Graphics
Intel® Iris® Xe MAX Graphics
Introduction¶
For 8-bit integer computation, a model must be quantized. You can use a quantized model from OpenVINO™ Toolkit Intel’s Pre-Trained Models or quantize a model yourself. For quantization, you can use the following:
Post-Training Optimization Tool delivered with the Intel® Distribution of OpenVINO™ toolkit release package
Neural Network Compression Framework available on GitHub: https://github.com/openvinotoolkit/nncf
The quantization process adds FakeQuantize layers on activations and weights for most layers. Read more about mathematical computations in the Uniform Quantization with Fine-Tuning.
When you pass the quantized IR to the OpenVINO™ plugin, the plugin automatically recognizes it as a quantized model and performs 8-bit inference. Note that if you pass a quantized model to another plugin that does not support 8-bit inference but supports all operations from the model, the model is inferred in precision that this plugin supports.
At runtime, the quantized model is loaded to the plugin. The plugin uses the Low Precision Transformation
component to update the model to infer it in low precision:
Update
FakeQuantize
layers to have quantized output tensors in low-precision range and add dequantization layers to compensate for the update. Dequantization layers are pushed through as many layers as possible to have more layers in low precision. After that, most layers have quantized input tensors in low-precision range and can be inferred in low precision. Ideally, dequantization layers should be fused in the nextFakeQuantize
layer.Weights are quantized and stored in
Constant
layers.
Prerequisites¶
Let’s explore quantized TensorFlow* implementation of the ResNet-50 model. Use Model Downloader to download the FP16
model from OpenVINO™ Toolkit - Open Model Zoo repository :
<omz_dir>//tools/downloader/downloader.py --name resnet-50-tf --precisions FP16-INT8
After that you should quantize the model with the Model Quantizer tool.
<omz_dir>//tools/downloader/quantizer.py --model_dir public/resnet-50-tf --dataset_dir <DATASET_DIR> --precisions=FP16-INT8
The simplest way to infer the model and collect performance counters is the C++ Benchmark Application.
./benchmark_app -m resnet-50-tf.xml -d CPU -niter 1 -api sync -report_type average_counters -report_folder pc_report_dir
If you infer the model with the OpenVINO™ CPU plugin and collect performance counters, all operations (except the last non-quantized SoftMax) are executed in INT8 precision.
Low-Precision 8-bit Integer Inference Workflow¶
For 8-bit integer computations, a model must be quantized. Quantized models can be downloaded from Overview of OpenVINO™ Toolkit Intel’s Pre-Trained Models. If the model is not quantized, you can use the Post-Training Optimization Tool to quantize the model. The quantization process adds FakeQuantize layers on activations and weights for most layers. Read more about mathematical computations in the Uniform Quantization with Fine-Tuning.
8-bit inference pipeline includes two stages (also refer to the figure below):
Offline stage, or model quantization. During this stage, FakeQuantize layers are added before most layers to have quantized tensors before layers in a way that low-precision accuracy drop for 8-bit integer inference satisfies the specified threshold. The output of this stage is a quantized model. Quantized model precision is not changed, quantized tensors are in original precision range (
fp32
).FakeQuantize
layer haslevels
attribute which defines quants count. Quants count defines precision which is used during inference. Forint8
rangelevels
attribute value has to be 255 or 256. To quantize the model, you can use the Post-Training Optimization Tool delivered with the Intel® Distribution of OpenVINO™ toolkit release package.When you pass the quantized IR to the OpenVINO™ plugin, the plugin automatically recognizes it as a quantized model and performs 8-bit inference. Note, if you pass a quantized model to another plugin that does not support 8-bit inference but supports all operations from the model, the model is inferred in precision that this plugin supports.
Runtime stage. This stage is an internal procedure of the OpenVINO™ plugin. During this stage, the quantized model is loaded to the plugin. The plugin uses
Low Precision Transformation
component to update the model to infer it in low precision:Update
FakeQuantize
layers to have quantized output tensors in low precision range and add dequantization layers to compensate the update. Dequantization layers are pushed through as many layers as possible to have more layers in low precision. After that, most layers have quantized input tensors in low precision range and can be inferred in low precision. Ideally, dequantization layers should be fused in the nextFakeQuantize
layer.Weights are quantized and stored in
Constant
layers.
![int8_flow]
Performance Counters¶
Information about layer precision is stored in the performance counters that are available from the Inference Engine API. For example, the part of performance counters table for quantized TensorFlow* implementation of ResNet-50 model inference on CPU Plugin looks as follows:
layerName |
execStatus |
layerType |
execType |
realTime (ms) |
cpuTime (ms) |
---|---|---|---|---|---|
resnet_model/batch_normalization_15/FusedBatchNorm/Add |
EXECUTED |
Convolution |
jit_avx512_1x1_I8 |
0.377 |
0.377 |
resnet_model/conv2d_16/Conv2D/fq_input_0 |
NOT_RUN |
FakeQuantize |
undef |
0 |
0 |
resnet_model/batch_normalization_16/FusedBatchNorm/Add |
EXECUTED |
Convolution |
jit_avx512_I8 |
0.499 |
0.499 |
resnet_model/conv2d_17/Conv2D/fq_input_0 |
NOT_RUN |
FakeQuantize |
undef |
0 |
0 |
resnet_model/batch_normalization_17/FusedBatchNorm/Add |
EXECUTED |
Convolution |
jit_avx512_1x1_I8 |
0.399 |
0.399 |
resnet_model/add_4/fq_input_0 |
NOT_RUN |
FakeQuantize |
undef |
0 |
0 |
resnet_model/add_4 |
NOT_RUN |
Eltwise |
undef |
0 |
0 |
resnet_model/add_5/fq_input_1 |
NOT_RUN |
FakeQuantize |
undef |
0 |
0 |
The exeStatus
column of the table includes possible values:
EXECUTED
- layer was executed by standalone primitive,NOT_RUN
- layer was not executed by standalone primitive or was fused with another operation and executed in another layer primitive.
The execType
column of the table includes inference primitives with specific suffixes. The layers have the following marks:
Suffix
I8
for layers that had 8-bit data type input and were computed in 8-bit precisionSuffix
FP32
for layers computed in 32-bit precision
All Convolution
layers are executed in int8 precision. Rest layers are fused into Convolutions using post operations optimization technique, which is described in Internal CPU Plugin Optimizations.