diff --git a/python/paddle/fluid/tests/unittests/test_async_ssa_graph_executor_mnist.py b/python/paddle/fluid/tests/unittests/test_async_ssa_graph_executor_mnist.py new file mode 100644 index 0000000000000000000000000000000000000000..e2b3b2b0f2dc7d04621274e5d761bb5c865abd9d --- /dev/null +++ b/python/paddle/fluid/tests/unittests/test_async_ssa_graph_executor_mnist.py @@ -0,0 +1,214 @@ +# Copyright (c) 2018 PaddlePaddle Authors. All Rights Reserved. +# +# Licensed 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. + +from __future__ import print_function + +import os +from PIL import Image +import numpy +import paddle +import paddle.fluid as fluid + +BATCH_SIZE = 64 +PASS_NUM = 5 + + +def loss_net(hidden, label): + prediction = fluid.layers.fc(input=hidden, size=10, act='softmax') + loss = fluid.layers.cross_entropy(input=prediction, label=label) + avg_loss = fluid.layers.mean(loss) + acc = fluid.layers.accuracy(input=prediction, label=label) + return prediction, avg_loss, acc + + +def convolutional_neural_network(img, label): + conv_pool_1 = fluid.nets.simple_img_conv_pool( + input=img, + filter_size=5, + num_filters=20, + pool_size=2, + pool_stride=2, + act="relu") + conv_pool_1 = fluid.layers.batch_norm(conv_pool_1) + conv_pool_2 = fluid.nets.simple_img_conv_pool( + input=conv_pool_1, + filter_size=5, + num_filters=50, + pool_size=2, + pool_stride=2, + act="relu") + return loss_net(conv_pool_2, label) + + +def train(use_cuda, + save_dirname=None, + model_filename=None, + params_filename=None): + if use_cuda and not fluid.core.is_compiled_with_cuda(): + return + + img = fluid.layers.data(name='img', shape=[1, 28, 28], dtype='float32') + label = fluid.layers.data(name='label', shape=[1], dtype='int64') + + prediction, avg_loss, acc = convolutional_neural_network(img, label) + + test_program = fluid.default_main_program().clone(for_test=True) + + optimizer = fluid.optimizer.Adam(learning_rate=0.001) + optimizer.minimize(avg_loss) + + def train_test(train_test_program, train_test_feed, train_test_reader): + acc_set = [] + avg_loss_set = [] + for test_data in train_test_reader(): + acc_np, avg_loss_np = exe.run(program=train_test_program, + feed=train_test_feed.feed(test_data), + fetch_list=[acc, avg_loss]) + acc_set.append(float(acc_np)) + avg_loss_set.append(float(avg_loss_np)) + # get test acc and loss + acc_val_mean = numpy.array(acc_set).mean() + avg_loss_val_mean = numpy.array(avg_loss_set).mean() + return avg_loss_val_mean, acc_val_mean + + place = fluid.CUDAPlace(0) if use_cuda else fluid.CPUPlace() + + exe = fluid.Executor(place) + + train_reader = paddle.batch( + paddle.reader.shuffle( + paddle.dataset.mnist.train(), buf_size=500), + batch_size=BATCH_SIZE) + test_reader = paddle.batch( + paddle.dataset.mnist.test(), batch_size=BATCH_SIZE) + feeder = fluid.DataFeeder(feed_list=[img, label], place=place) + + exe.run(fluid.default_startup_program()) + main_program = fluid.default_main_program() + + exec_strategy = fluid.ExecutionStrategy() + build_strategy = fluid.BuildStrategy() + + cpu_num = int(os.environ.get('CPU_NUM')) + thread_num = int(os.getenv("NUM_THREADS")) + + print("cpu_num:" + str(cpu_num)) + print("thread_num:" + str(thread_num)) + + build_strategy.async_mode = True + + exec_strategy.num_threads = thread_num + exec_strategy.num_iteration_per_drop_scope = 1 + exec_strategy.num_iteration_per_run = 10 + + pe = fluid.ParallelExecutor( + use_cuda=False, + loss_name=avg_loss.name, + main_program=main_program, + build_strategy=build_strategy, + exec_strategy=exec_strategy) + + lists = [] + step = 0 + for epoch_id in range(PASS_NUM): + for step_id, data in enumerate(train_reader()): + loss_val, acc_val = pe.run(feed=feeder.feed(data), + fetch_list=[avg_loss.name, acc.name]) + loss_val = numpy.mean(loss_val) + acc_val = numpy.mean(acc_val) + if step % 100 == 0: + print("Pass %d, Batch %d, Cost %f" % (epoch_id, step, loss_val)) + step += 1 + # test for epoch + avg_loss_val, acc_val = train_test( + train_test_program=test_program, + train_test_reader=test_reader, + train_test_feed=feeder) + + print("Test with Epoch %d, avg_cost: %s, acc: %s" % + (epoch_id, avg_loss_val, acc_val)) + lists.append((epoch_id, avg_loss_val, acc_val)) + if save_dirname is not None: + fluid.io.save_inference_model( + save_dirname, ["img"], [prediction], + exe, + model_filename=model_filename, + params_filename=params_filename) + + # find the best pass + best = sorted(lists, key=lambda list: float(list[1]))[0] + print('Best pass is %s, testing Avgcost is %s' % (best[0], best[1])) + print('The classification accuracy is %.2f%%' % (float(best[2]) * 100)) + + +def infer(use_cuda, + save_dirname=None, + model_filename=None, + params_filename=None): + if save_dirname is None: + return + + place = fluid.CUDAPlace(0) if use_cuda else fluid.CPUPlace() + exe = fluid.Executor(place) + + def load_image(file): + im = Image.open(file).convert('L') + im = im.resize((28, 28), Image.ANTIALIAS) + im = numpy.array(im).reshape(1, 1, 28, 28).astype(numpy.float32) + im = im / 255.0 * 2.0 - 1.0 + return im + + cur_dir = os.path.dirname(os.path.realpath(__file__)) + tensor_img = load_image(cur_dir + '/image/infer_3.png') + + inference_scope = fluid.core.Scope() + with fluid.scope_guard(inference_scope): + # Use fluid.io.load_inference_model to obtain the inference program desc, + # the feed_target_names (the names of variables that will be feeded + # data using feed operators), and the fetch_targets (variables that + # we want to obtain data from using fetch operators). + [inference_program, feed_target_names, + fetch_targets] = fluid.io.load_inference_model( + save_dirname, exe, model_filename, params_filename) + + # Construct feed as a dictionary of {feed_target_name: feed_target_data} + # and results will contain a list of data corresponding to fetch_targets. + results = exe.run(inference_program, + feed={feed_target_names[0]: tensor_img}, + fetch_list=fetch_targets) + lab = numpy.argsort(results) + print("Inference result of image/infer_3.png is: %d" % lab[0][0][-1]) + + +def main(use_cuda): + model_filename = None + params_filename = None + save_dirname = "recognize_digits" + ".inference.model" + + # call train() with is_local argument to run distributed train + train( + use_cuda=use_cuda, + save_dirname=save_dirname, + model_filename=model_filename, + params_filename=params_filename) + infer( + use_cuda=use_cuda, + save_dirname=save_dirname, + model_filename=model_filename, + params_filename=params_filename) + + +if __name__ == '__main__': + use_cuda = False + main(use_cuda=use_cuda)