Comment on page
The following example uses a simple QAT PyTorch model that implements a fully connected neural network with two hidden layers. Due to its small size, making this model respect FHE constraints is relatively easy.
import brevitas.nn as qnn
import torch.nn as nn
N_FEAT = 12
n_bits = 3
def __init__(self, n_hidden):
self.quant_inp = qnn.QuantIdentity(bit_width=n_bits, return_quant_tensor=True)
self.fc1 = qnn.QuantLinear(N_FEAT, n_hidden, True, weight_bit_width=n_bits, bias_quant=None)
self.quant2 = qnn.QuantIdentity(bit_width=n_bits, return_quant_tensor=True)
self.fc2 = qnn.QuantLinear(n_hidden, n_hidden, True, weight_bit_width=n_bits, bias_quant=None)
self.quant3 = qnn.QuantIdentity(bit_width=n_bits, return_quant_tensor=True)
self.fc3 = qnn.QuantLinear(n_hidden, 2, True, weight_bit_width=n_bits, bias_quant=None)
def forward(self, x):
x = self.quant_inp(x)
x = self.quant2(torch.relu(self.fc1(x)))
x = self.quant3(torch.relu(self.fc2(x)))
x = self.fc3(x)
Once the model is trained, calling the
compile_brevitas_qat_modelfrom Concrete ML will automatically perform conversion and compilation of a QAT network. Here, 3-bit quantization is used for both the weights and activations. The
compile_brevitas_qat_modelfunction automatically identifies the number of quantization bits used in the Brevitas model.
from concrete.ml.torch.compile import compile_brevitas_qat_model
torch_input = torch.randn(100, N_FEAT)
torch_model = QATSimpleNet(30)
quantized_module = compile_brevitas_qat_model(
torch_model, # our model
torch_input, # a representative input-set to be used for both quantization and compilation
The PyTorch/Brevitas models, created following the example above, require the user to configure quantization parameters such as
bit_width(activation bit-width) and
weight_bit_width. The quantization parameters, along with the number of neurons on each layer, will determine the accumulator bit-width of the network. Larger accumulator bit-widths result in higher accuracy but slower FHE inference time.
The following configurations were determined through experimentation for convolutional and dense layers.
Using the templates above, the probability of obtaining the target accumulator bit-width, for a single layer, was determined experimentally by training 10 models for each of the following data-sets.
Note that the accuracy on larger data-sets, when the accumulator size is low, is also reduced strongly.
The model can now perform encrypted inference.
x_test = numpy.array([numpy.random.randn(N_FEAT)])
y_pred = quantized_module.forward(x_test, fhe="execute")
In this example, the input values
x_testand the predicted values
y_predare floating points. The quantization (resp. de-quantization) step is done in the clear within the
forwardmethod, before (resp. after) any FHE computations.
The user can also perform the inference on clear data. Two approaches exist:
quantized_module.forward(quantized_x, fhe="simulate"): simulates FHE execution taking into account Table Lookup errors. De-quantization must be done in a second step as for actual FHE execution. Simulation takes into account the
quantized_module.forward(quantized_x, fhe="disable"): computes predictions in the clear on quantized data, and then de-quantize the result. The return value of this function contains the de-quantized (float) output of running the model in the clear. Calling this function on clear data is useful when debugging, but this does not perform actual FHE simulation.
FHE simulation allows to measure the impact of the Table Lookup error on the model accuracy. The Table Lookup error can be adjusted using
global_p_error, as described in the approximate computation section.
While the example above shows how to import a Brevitas/PyTorch model, Concrete ML also provides an option to import generic QAT models implemented in PyTorch or through ONNX. Deep learning models made with TensorFlow or Keras should be usable by preliminary converting them to ONNX.
QAT models contain quantizers in the PyTorch graph. These quantizers ensure that the inputs to the Linear/Dense and Conv layers are quantized.
n_bits_qatis the bit-width of activations and weights during the QAT process. To import a PyTorch QAT network, you can use the
compile_torch_modellibrary function, passing
from concrete.ml.torch.compile import compile_torch_model
n_bits_qat = 3
quantized_module = compile_torch_model(
When importing QAT models using this generic pipeline, a representative calibration set should be given as quantization parameters in the model need to be inferred from the statistics of the values encountered during inference.
Concrete ML supports a variety of PyTorch operators that can be used to build fully connected or convolutional neural networks, with normalization and activation layers. Moreover, many element-wise operators are supported.
Concrete ML supports these operators but also the QAT equivalents from Brevitas.
The equivalent versions from
torch.functionalare also supported.