anijain2305 commented on a change in pull request #4667: [Tutorial] Deploy Quantized Model on CUDA URL: https://github.com/apache/incubator-tvm/pull/4667#discussion_r364867350
########## File path: tutorials/frontend/deploy_quantized.py ########## @@ -0,0 +1,154 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. See the NOTICE file +# distributed with this work for additional information +# regarding copyright ownership. The ASF licenses this file +# to you under the Apache License, Version 2.0 (the +# "License"); you may not use this file except in compliance +# with the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, +# software distributed under the License is distributed on an +# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY +# KIND, either express or implied. See the License for the +# specific language governing permissions and limitations +# under the License. +""" +Deploy a Quantized Model on Cuda +================================ +**Author**: `Wuwei Lin <https://github.com/vinx13>`_ + +This article is an introductory tutorial of automatic quantization with TVM. +We will import a GluonCV pre-trained model on ImageNet to Relay, quantize the Relay model +and then perform the inference. +""" + +import tvm +from tvm import relay +from tvm.relay import quantize as qtz +import mxnet as mx +from tvm.contrib.download import download_testdata +from mxnet import gluon +import logging +import os + +batch_size = 1 +model_name = "resnet18_v1" +target = 'cuda' +ctx = tvm.context(target) + +############################################################################### +# Prepare the Dataset +# ------------------- +# We will demonstrate how to prepare the calibration dataset for quantization. +# We first download the validate set of ImageNet and pre-process the dataset. +calibration_rec = download_testdata( + 'http://data.mxnet.io.s3-website-us-west-1.amazonaws.com/data/val_256_q90.rec', + 'val_256_q90.rec') + +def get_val_data(num_workers=4): + mean_rgb = [123.68, 116.779, 103.939] + std_rgb = [58.393, 57.12, 57.375] + + def batch_fn(batch): + return batch.data[0].asnumpy(), batch.label[0].asnumpy() + + img_size = 299 if model_name == 'inceptionv3' else 224 + val_data = mx.io.ImageRecordIter( + path_imgrec=calibration_rec, + preprocess_threads=num_workers, + shuffle=False, + batch_size=batch_size, + resize=256, + data_shape=(3, img_size, img_size), + mean_r=mean_rgb[0], + mean_g=mean_rgb[1], + mean_b=mean_rgb[2], + std_r=std_rgb[0], + std_g=std_rgb[1], + std_b=std_rgb[2], + ) + return val_data, batch_fn + + +############################################################################### +# The calibration dataset should be a iterable object. We define the +# calibration dataset as a generator object in Python. In this tutorials, we Review comment: tutorials -> tutorial ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
