Cross-Layer Equalization with QuantSim

This notebook contains an example of how to use AIMET to apply Cross-Layer Equalization (CLE) and use quantization simulation (QuantSim). CLE is post-training quantization technique for improving quantized accuracy of a model. This technique help recover quantized accuracy when the model quantization is sensitive to parameter quantization as opposed to activation quantization.

CLE does not need any data samples.

Cross-layer equalization

AIMET performs the following steps when running CLE:

  1. Batch norm (BN) Folding: Folds BN layers into convolution (Conv) layers immediate before or after the Conv layers.

  2. Cross-layer scaling: For a set of consecutive Conv layers, equalizes the range of tensor values per-channel by scaling their weight tensor values.

  3. High bias folding: Cross-layer scaling may result in high bias parameter values for some layers. This technique folds some of the bias of a layer into the subsequent layer’s parameters.

Bias Correction

Quantization sometimes leads to a shift in layer outputs. Bias correction helps correct this shift by adjusting the bias parameters of that layer. This step is optional, and is applied after CLE.

Overall flow

This example performs the following steps:

  1. Instantiate the example evaluation and training pipeline

  2. Load the FP32 model and evaluate the model to find the baseline FP32 accuracy

  3. Create a quantization simulation model (with fake quantization ops inserted) and evaluate this simuation model

  4. Apply CLE, and evaluate the simulation model

  5. Export the simulation model encodings and how to take them to SNPE/QNN

Note

This notebook does not show state-of-the-art results. For example, it uses a relatively quantization-friendly model (Resnet18). Also, some optimization parameters like number of fine-tuning epochs are chosen to improve execution speed in the notebook.

Dataset

This example does image classification on the ImageNet dataset. If you already have a version of the data set, use that. Otherwise download the data set, for example from https://image-net.org/challenges/LSVRC/2012/index .

Note

To speed up the execution of this notebook, you can use a reduced subset of the ImageNet dataset. For example: The entire ILSVRC2012 dataset has 1000 classes, 1000 training samples per class and 50 validation samples per class. However, for the purpose of running this notebook, you can reduce the dataset to, say, two samples per class.

Edit the cell below to specify the directory where the downloaded ImageNet dataset is saved.

[ ]:

DATASET_DIR = "/path/to/dataset/dir/"  # Replace this path with a real directory

1. Instantiate the example training and validation pipeline

Use the following training and validation loop for the image classification task.

Things to note:

  • AIMET does not put limitations on how the training and validation pipeline is written. AIMET modifies the user’s model to create a QuantizationSim model, which is still a PyTorch model. The QuantizationSim model can be used in place of the original model when doing inference or training.

  • AIMET doesn not put limitations on the interface of the evaluate() or train() methods. You should be able to use your existing evaluate and train routines as-is.

[ ]:

import tensorflow as tf
from Examples.common import image_net_config
from Examples.tensorflow.utils.keras.image_net_dataset import ImageNetDataset
from Examples.tensorflow.utils.keras.image_net_evaluator import ImageNetEvaluator


class ImageNetDataPipeline:
    """
    Provides APIs for model evaluation and finetuning using ImageNet Dataset.
    """

    @staticmethod
    def get_val_dataset() -> tf.data.Dataset:
        """
        Instantiates a validation dataloader for ImageNet dataset and returns it
        :return: A tensorflow dataset
        """
        data_loader = ImageNetDataset(DATASET_DIR,
                                      image_size=image_net_config.dataset['image_size'],
                                      batch_size=image_net_config.evaluation['batch_size'])

        return data_loader

    @staticmethod
    def evaluate(model, iterations=None) -> float:
        """
        Given a Keras model, evaluates its Top-1 accuracy on the validation dataset
        :param model: The Keras model to be evaluated.
        :param iterations: The number of iterations to run. If None, all the data will be used
        :return: The accuracy for the sample with the maximum accuracy.
        """
        evaluator = ImageNetEvaluator(DATASET_DIR,
                                      image_size=image_net_config.dataset["image_size"],
                                      batch_size=image_net_config.evaluation["batch_size"])

        return evaluator.evaluate(model=model, iterations=iterations)

2. Load the model and evaluate to get a baseline FP32 accuracy score

2.1 Load a pretrained ResNet50 model from Keras.

You can load any pretrained Keras model instead.

[ ]:

from tensorflow.keras.applications.resnet50 import ResNet50

model = ResNet50(include_top=True,
                 weights="imagenet",
                 input_tensor=None,
                 input_shape=None,
                 pooling=None,
                 classes=1000)

2.2 Compute the floating point 32-bit (FP32) accuracy of this model using the evaluate() routine.

[ ]:

ImageNetDataPipeline.evaluate(model=model, iterations=10)

3. Create a quantization simulation model and determine quantized accuracy

Fold Batch Normalization layers

Before calculating the simulated quantized accuracy using QuantizationSimModel, fold the BatchNormalization (BN) layers into adjacent Convolutional layers. The BN layers that cannot be folded are left as they are.

BN folding improves inference performance on quantized runtimes but can degrade accuracy on these platforms. This step simulates this on-target drop in accuracy.

The following code calls AIMET to fold the BN layers of a given model. NOTE: During folding, a new model is returned. Please use the returned model for the rest of the pipeline.

3.1 Use the following code to call AIMET to fold the BN layers on the model.

Note

Folding returns a new model. Use the returned model for the rest of the pipeline.

[ ]:

from aimet_tensorflow.keras.batch_norm_fold import fold_all_batch_norms

_, model = fold_all_batch_norms(model)

Create the Quantization Sim Model

3.2 Use AIMET to create a QuantizationSimModel.

In this step, AIMET inserts fake quantization ops in the model graph and configures them.

Key parameters:

  • Setting default_output_bw to 8 performs all activation quantizations in the model using integer 8-bit precision

  • Setting default_param_bw to 8 performs all parameter quantizations in the model using integer 8-bit precision

See QuantizationSimModel in the AIMET API documentation for a full explanation of the parameters.

[ ]:

from aimet_common.defs import QuantScheme
from aimet_tensorflow.keras.quantsim import QuantizationSimModel

sim = QuantizationSimModel(model=model,
                           quant_scheme=QuantScheme.post_training_tf,
                           rounding_mode="nearest",
                           default_output_bw=8,
                           default_param_bw=8)

AIMET has added quantizer nodes to the model graph, but before the sim model can be used for inference or training, scale and offset quantization parameters must be calculated for each quantizer node by passing unlabeled data samples through the model to collect range statistics. This process is sometimes referred to as calibration. AIMET refers to it as “computing encodings”.

3.3 Create a routine to pass unlabeled data samples through the model.

The following code is one way to write a routine that passes unlabeled samples through the model to compute encodings. It uses the existing train or validation data loader to extract samples and pass them to the model. Since there is no need to compute loss metrics, it ignores the model output.

[ ]:

from tensorflow.keras.utils import Progbar
from tensorflow.keras.applications.resnet import preprocess_input

def pass_calibration_data(sim_model, samples):
    tf_dataset = ImageNetDataPipeline.get_val_dataset()
    dataset = tf_dataset.dataset
    batch_size = tf_dataset.batch_size

    progbar = Progbar(samples)

    batch_cntr = 0
    for inputs, _ in dataset:
        sim_model(preprocess_input(inputs))

        batch_cntr += 1
        progbar_stat_update = \
            batch_cntr * batch_size if (batch_cntr * batch_size) < samples else samples
        progbar.update(progbar_stat_update)
        if (batch_cntr * batch_size) > samples:
            break

A few notes regarding the data samples:

  • A very small percentage of the data samples are needed. For example, the training dataset for ImageNet has 1M samples; 500 or 1000 suffice to compute encodings.

  • The samples should be reasonably well distributed. While it’s not necessary to cover all classes, avoid extreme scenarios like using only dark or only light samples. That is, using only pictures captured at night, say, could skew the results.

3.4 Call AIMET to pass data through the model and compute the quantization encodings.

Encodings here refer to scale and offset quantization parameters.

[ ]:

sim.compute_encodings(forward_pass_callback=pass_calibration_data,
                      forward_pass_callback_args=1000)

3.5 Determine the simulated quantized accuracy of the equalized model. Create a simulation model like before and evaluate it to calculate accuracy.

[ ]:

ImageNetDataPipeline.evaluate(sim.model)

4. Apply CLE

4.1 Perform CLE.

The next cell performs cross-layer equalization on the model. As noted before, the function folds batch norms, applies cross-layer scaling, and then folds high biases.

Note

The CLE procedure needs BN statistics. If a BN folded model is provided, CLE runs the cross-layer scaling (CLS) optimization step but skips the high-bias absorption (HBA) step. To avoid this, load the original model again before running CLE.

[ ]:

from aimet_tensorflow.keras import cross_layer_equalization as aimet_cle

cle_applied_model = aimet_cle.equalize_model(model)

4.2 Compute the accuracy of the equalized model.

Create a simulation model as before and evaluate it to determine simulated quantized accuracy.

[ ]:

sim = QuantizationSimModel(model=cle_applied_model,
                           quant_scheme=QuantScheme.post_training_tf,
                           rounding_mode="nearest",
                           default_output_bw=8,
                           default_param_bw=8)

sim.compute_encodings(forward_pass_callback=pass_calibration_data,
                      forward_pass_callback_args=1000)

ImageNetDataPipeline.evaluate(sim.model)

There might be little gain in accuracy after this limited application of CLE. Experiment with the hyper-parameters to get better results.

Next steps

The next step is to export this model for installation on the target.

Export the model and encodings.

  • Export the model with the updated weights but without the fake quant ops.

  • Export the encodings (scale and offset quantization parameters). AIMET QuantizationSimModel provides an export API for this purpose.

The following code performs these exports.

[ ]:

import os

os.makedirs("./output/", exist_ok=True)
sim.export(path="./output", filename_prefix="resnet50_after_cle")

For more information

See the AIMET API docs for details about the AIMET APIs and optional parameters.

See the other example notebooks to learn how to use other AIMET post-training quantization techniques.

For more information about CLE, see “Data-Free Quantization Through Weight Equalization and Bias Correction”, ICCV 2019 - https://arxiv.org/abs/1906.04721