huajsj commented on code in PR #11557: URL: https://github.com/apache/tvm/pull/11557#discussion_r926300278
########## gallery/how_to/work_with_relay/using_with_pipeline_executor.py: ########## @@ -0,0 +1,262 @@ +# 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. +""" +Using Pipeline Executor in Relay +================================= +**Author**: `Hua Jiang <https://https://github.com/huajsj>`_ + +This is a short tutorial on how to use "Pipeline Executor" with Relay. +""" +import tvm +from tvm import te +import numpy as np +from tvm.contrib import graph_executor as runtime +from tvm.relay.op.contrib.cutlass import partition_for_cutlass +from tvm import relay +from tvm.relay import testing +import tvm.testing +import time +from tvm.contrib.cutlass import ( + has_cutlass, + num_cutlass_partitions, + finalize_modules, + finalize_modules_vm, +) + +img_size = 8 +####################################################################### +# Create a simple network, this network can be a pre-trained model too. +# --------------------------------------------------------------------- +# Let's create a very simple network for demonstration. +# It consists of convolution, batch normalization, and ReLU activation. +def get_network(): + out_channels = 16 + batch_size = 1 + data = relay.var("data", relay.TensorType((batch_size, 3, img_size, img_size), "float16")) + dense_weight = relay.var( + "dweight", relay.TensorType((batch_size, 16 * img_size * img_size), "float16") + ) + weight = relay.var("weight") + second_weight = relay.var("second_weight") + bn_gamma = relay.var("bn_gamma") + bn_beta = relay.var("bn_beta") + bn_mmean = relay.var("bn_mean") + bn_mvar = relay.var("bn_var") + simple_net = relay.nn.conv2d( + data=data, weight=weight, kernel_size=(3, 3), channels=out_channels, padding=(1, 1) + ) + simple_net = relay.nn.batch_norm(simple_net, bn_gamma, bn_beta, bn_mmean, bn_mvar)[0] + simple_net = relay.nn.relu(simple_net) + simple_net = relay.nn.batch_flatten(simple_net) + simple_net = relay.nn.dense(simple_net, dense_weight) + simple_net = relay.Function(relay.analysis.free_vars(simple_net), simple_net) + data_shape = (batch_size, 3, img_size, img_size) + net, params = testing.create_workload(simple_net) + return net, params, data_shape + + +net, params, data_shape = get_network() +########################################### +# Splitting the network into two subgraphs. +# ----------------------------------------- +# We use an testing linear graph splitting function as a example. User also can create their +# own splitting function logic. Review Comment: It is an example that the graph splitting function comes from a unit test. User can create a customized function to split the graph. -- 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. To unsubscribe, e-mail: commits-unsubscr...@tvm.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
