High Granularity Quantization 2
HGQ2 (High Granularity Quantization 2) is a quantization-aware training framework built on Keras v3, targeting real-time deep learning applications on edge devices like FPGAs. It provides a comprehensive set of tools for creating and training quantized neural networks with minimal effort.
HGQ2 implements an gradient-based automatic bitwidth optimization and quantization-aware training algorithm. By laveraging gradients, it allows for bitwidth optimization at arbitrary granularity, up to per-weight and per-activation level.
Key Features
Multi-backend support: Works with TensorFlow, JAX, and PyTorch through Keras v3
Flexible quantization: Supports different quantization schemes including fixed-point and minifloat
Hardware synthesis: Direct integration with hls4ml for FPGA deployment
Trainable quantization parameters: Optimize bitwidths through gradient-based methods
Effective Bit-Operations (EBOP): Accurate resource estimation during training for the deployed firmware
Advanced layer support: HGQ2 supports advanced layers like einsum, einsum dense, and multi-head attention layers with quantization and hardware synthesis support
import keras
from hgq.layers import QDense, QConv2D
from hgq.config import LayerConfigScope, QuantizerConfigScope
# Setup quantization configuration
# These values are the defaults, just for demonstration purposes here
with (
# Configuration scope for setting the default quantization type and overflow mode
# The second configuration scope overrides the first one for the 'datalane' place
QuantizerConfigScope(place='all', default_q_type='kbi', overflow_mode='SAT_SYM'),
# Configuration scope for enabling EBOPs and setting the beta0 value
QuantizerConfigScope(place='datalane', default_q_type='kif', overflow_mode='WRAP'),
LayerConfigScope(enable_ebops=True, beta0=1e-5),
):
model = keras.Sequential([
QConv2D(32, (3, 3), activation='relu'),
keras.layers.MaxPooling2D((2, 2)),
keras.layers.Flatten(),
QDense(10)
])
Index
API Reference:
- hgq package
- hgq.config package
- hgq.constraints package
- hgq.layers package
- Subpackages
- Submodules
- hgq.layers.activation module
- hgq.layers.batch_normalization module
- hgq.layers.conv module
- hgq.layers.einsum_dense_batchnorm module
- hgq.layers.linformer_attention module
- hgq.layers.multi_head_attention module
- hgq.layers.pooling module
- hgq.layers.softmax module
- Module contents
QAddQAveragePooling1DQAveragePooling2DQAveragePooling3DQAveragePow2QAvgPool1DQAvgPool2DQAvgPool3DQBatchNormDenseQBatchNormalizationQConv1DQConv2DQConv3DQDenseQDotQEinsumQEinsumDenseQEinsumDenseBatchnormQGlobalAveragePooling1DQGlobalAveragePooling2DQGlobalAveragePooling3DQGlobalAvgPool1DQGlobalAvgPool2DQGlobalAvgPool3DQGlobalMaxPool1DQGlobalMaxPool2DQGlobalMaxPool3DQGlobalMaxPooling1DQGlobalMaxPooling2DQGlobalMaxPooling3DQLinformerAttentionQMaxPool1DQMaxPool2DQMaxPool3DQMaxPooling1DQMaxPooling2DQMaxPooling3DQMaximumQMeanPow2QMinimumQMultiHeadAttentionQMultiplyQSoftmaxQSubtractQSumQUnaryFunctionLUTQuantizer
- hgq.quantizer package
- hgq.regularizers package
- hgq.utils package
- qkeras package