From e5a1abfe0b74af278f13c0e21184f6aeaf3d05d4 Mon Sep 17 00:00:00 2001 From: zhang wenhui Date: Thu, 28 Nov 2019 16:12:48 +0800 Subject: [PATCH] cherry-pick 1.6 to develop (#4004) --- PaddleRec/gru4rec/README.md | 5 +- PaddleRec/gru4rec/convert_format.py | 4 +- PaddleRec/gru4rec/infer.py | 1 + PaddleRec/gru4rec/infer_sample_neg.py | 1 + PaddleRec/gru4rec/net.py | 60 ++++++++++++------------ PaddleRec/gru4rec/text2paddle.py | 33 +++++++++---- PaddleRec/gru4rec/train.py | 18 +++---- PaddleRec/gru4rec/train_sample_neg.py | 1 + PaddleRec/gru4rec/utils.py | 24 ++++++++-- PaddleRec/multiview_simnet/README.md | 2 + PaddleRec/multiview_simnet/infer.py | 17 +++++++ PaddleRec/multiview_simnet/nets.py | 67 ++++++++++++++++----------- PaddleRec/multiview_simnet/train.py | 23 +++++++-- PaddleRec/ssr/README.md | 6 ++- PaddleRec/ssr/infer.py | 1 + PaddleRec/ssr/nets.py | 17 +++---- PaddleRec/ssr/reader.py | 5 +- PaddleRec/ssr/train.py | 20 ++++---- PaddleRec/ssr/utils.py | 23 +++++++-- PaddleRec/tagspace/README.md | 2 + PaddleRec/tagspace/infer.py | 1 + PaddleRec/tagspace/net.py | 61 ++++++++++++++---------- PaddleRec/tagspace/text2paddle.py | 45 ++++++++++++------ PaddleRec/tagspace/train.py | 24 +++++----- PaddleRec/tagspace/utils.py | 51 ++++++++++++++++---- PaddleRec/word2vec/README.md | 12 +++-- PaddleRec/word2vec/infer.py | 41 ++++++++-------- PaddleRec/word2vec/net.py | 53 +++++++++------------ PaddleRec/word2vec/preprocess.py | 14 ++++-- PaddleRec/word2vec/train.py | 7 +++ PaddleRec/word2vec/utils.py | 24 ++++++++-- 31 files changed, 432 insertions(+), 231 deletions(-) diff --git a/PaddleRec/gru4rec/README.md b/PaddleRec/gru4rec/README.md index b60e4f29..15a9b106 100644 --- a/PaddleRec/gru4rec/README.md +++ b/PaddleRec/gru4rec/README.md @@ -45,6 +45,9 @@ session-based推荐应用场景非常广泛，比如用户的商品浏览、新 运行样例程序可跳过'RSC15 数据下载及预处理'部分 + +**要求使用PaddlePaddle 1.6及以上版本或适当的develop版本。** + 同时推荐用户参考[ IPython Notebook demo](https://aistudio.baidu.com/aistudio/projectDetail/122296) ## RSC15 数据下载及预处理 @@ -278,7 +281,7 @@ model:model_r@20/epoch_10 recall@20:0.681 time_cost(s):12.2 可参考cluster_train.py 配置其他多机环境 -运行命令本地模拟多机场景 +运行命令本地模拟多机场景, 暂不支持windows ``` sh cluster_train.sh ``` diff --git a/PaddleRec/gru4rec/convert_format.py b/PaddleRec/gru4rec/convert_format.py index b5db511e..7bca1d52 100644 --- a/PaddleRec/gru4rec/convert_format.py +++ b/PaddleRec/gru4rec/convert_format.py @@ -2,8 +2,8 @@ import sys def convert_format(input, output): - with open(input) as rf: - with open(output, "w") as wf: + with open(input, "r", encoding='utf-8') as rf: + with open(output, "w", encoding='utf-8') as wf: last_sess = -1 sign = 1 i = 0 diff --git a/PaddleRec/gru4rec/infer.py b/PaddleRec/gru4rec/infer.py index bc459c28..032205cf 100644 --- a/PaddleRec/gru4rec/infer.py +++ b/PaddleRec/gru4rec/infer.py @@ -71,6 +71,7 @@ def infer(test_reader, use_cuda, model_path): if __name__ == "__main__": + utils.check_version() args = parse_args() start_index = args.start_index last_index = args.last_index diff --git a/PaddleRec/gru4rec/infer_sample_neg.py b/PaddleRec/gru4rec/infer_sample_neg.py index 48458e82..b77f3685 100644 --- a/PaddleRec/gru4rec/infer_sample_neg.py +++ b/PaddleRec/gru4rec/infer_sample_neg.py @@ -84,6 +84,7 @@ def infer(args, vocab_size, test_reader, use_cuda): if __name__ == "__main__": + utils.check_version() args = parse_args() start_index = args.start_index last_index = args.last_index diff --git a/PaddleRec/gru4rec/net.py b/PaddleRec/gru4rec/net.py index 6a715443..4bdfcdfa 100644 --- a/PaddleRec/gru4rec/net.py +++ b/PaddleRec/gru4rec/net.py @@ -10,12 +10,12 @@ def all_vocab_network(vocab_size, gru_lr_x = 1.0 fc_lr_x = 1.0 # Input data - src_wordseq = fluid.layers.data( - name="src_wordseq", shape=[1], dtype="int64", lod_level=1) - dst_wordseq = fluid.layers.data( - name="dst_wordseq", shape=[1], dtype="int64", lod_level=1) + src_wordseq = fluid.data( + name="src_wordseq", shape=[None, 1], dtype="int64", lod_level=1) + dst_wordseq = fluid.data( + name="dst_wordseq", shape=[None, 1], dtype="int64", lod_level=1) - emb = fluid.layers.embedding( + emb = fluid.embedding( input=src_wordseq, size=[vocab_size, hid_size], param_attr=fluid.ParamAttr( @@ -56,19 +56,20 @@ def train_bpr_network(vocab_size, neg_size, hid_size, drop_out=0.2): gru_lr_x = 1.0 fc_lr_x = 1.0 # Input data - src = fluid.layers.data(name="src", shape=[1], dtype="int64", lod_level=1) - pos_label = fluid.layers.data( - name="pos_label", shape=[1], dtype="int64", lod_level=1) - label = fluid.layers.data( - name="label", shape=[neg_size + 1], dtype="int64", lod_level=1) + src = fluid.data(name="src", shape=[None, 1], dtype="int64", lod_level=1) + pos_label = fluid.data( + name="pos_label", shape=[None, 1], dtype="int64", lod_level=1) + label = fluid.data( + name="label", shape=[None, neg_size + 1], dtype="int64", lod_level=1) - emb_src = fluid.layers.embedding( + emb_src = fluid.embedding( input=src, size=[vocab_size, hid_size], param_attr=fluid.ParamAttr( name="emb", initializer=fluid.initializer.XavierInitializer(), learning_rate=emb_lr_x)) + emb_src = fluid.layers.squeeze(input=emb_src, axes=[1]) emb_src_drop = fluid.layers.dropout(emb_src, dropout_prob=drop_out) @@ -90,7 +91,7 @@ def train_bpr_network(vocab_size, neg_size, hid_size, drop_out=0.2): gru_h0_drop = fluid.layers.dropout(gru_h0, dropout_prob=drop_out) label_re = fluid.layers.sequence_reshape(input=label, new_dim=1) - emb_label = fluid.layers.embedding( + emb_label1 = fluid.embedding( input=label_re, size=[vocab_size, hid_size], param_attr=fluid.ParamAttr( @@ -98,6 +99,7 @@ def train_bpr_network(vocab_size, neg_size, hid_size, drop_out=0.2): initializer=fluid.initializer.XavierInitializer(), learning_rate=emb_lr_x)) + emb_label = fluid.layers.squeeze(input=emb_label1, axes=[1]) emb_label_drop = fluid.layers.dropout(emb_label, dropout_prob=drop_out) gru_exp = fluid.layers.expand( @@ -120,19 +122,20 @@ def train_cross_entropy_network(vocab_size, neg_size, hid_size, drop_out=0.2): gru_lr_x = 1.0 fc_lr_x = 1.0 # Input data - src = fluid.layers.data(name="src", shape=[1], dtype="int64", lod_level=1) - pos_label = fluid.layers.data( - name="pos_label", shape=[1], dtype="int64", lod_level=1) - label = fluid.layers.data( - name="label", shape=[neg_size + 1], dtype="int64", lod_level=1) + src = fluid.data(name="src", shape=[None, 1], dtype="int64", lod_level=1) + pos_label = fluid.data( + name="pos_label", shape=[None, 1], dtype="int64", lod_level=1) + label = fluid.data( + name="label", shape=[None, neg_size + 1], dtype="int64", lod_level=1) - emb_src = fluid.layers.embedding( + emb_src = fluid.embedding( input=src, size=[vocab_size, hid_size], param_attr=fluid.ParamAttr( name="emb", initializer=fluid.initializer.XavierInitializer(), learning_rate=emb_lr_x)) + emb_src = fluid.layers.squeeze(input=emb_src, axes=[1]) emb_src_drop = fluid.layers.dropout(emb_src, dropout_prob=drop_out) @@ -154,13 +157,14 @@ def train_cross_entropy_network(vocab_size, neg_size, hid_size, drop_out=0.2): gru_h0_drop = fluid.layers.dropout(gru_h0, dropout_prob=drop_out) label_re = fluid.layers.sequence_reshape(input=label, new_dim=1) - emb_label = fluid.layers.embedding( + emb_label1 = fluid.embedding( input=label_re, size=[vocab_size, hid_size], param_attr=fluid.ParamAttr( name="emb", initializer=fluid.initializer.XavierInitializer(), learning_rate=emb_lr_x)) + emb_label = fluid.layers.squeeze(input=emb_label1, axes=[1]) emb_label_drop = fluid.layers.dropout(emb_label, dropout_prob=drop_out) @@ -180,8 +184,8 @@ def train_cross_entropy_network(vocab_size, neg_size, hid_size, drop_out=0.2): def infer_network(vocab_size, batch_size, hid_size, dropout=0.2): - src = fluid.layers.data(name="src", shape=[1], dtype="int64", lod_level=1) - emb_src = fluid.layers.embedding( + src = fluid.data(name="src", shape=[None, 1], dtype="int64", lod_level=1) + emb_src = fluid.embedding( input=src, size=[vocab_size, hid_size], param_attr="emb") emb_src_drop = fluid.layers.dropout( emb_src, dropout_prob=dropout, is_test=True) @@ -198,20 +202,18 @@ def infer_network(vocab_size, batch_size, hid_size, dropout=0.2): gru_h0_drop = fluid.layers.dropout( gru_h0, dropout_prob=dropout, is_test=True) - all_label = fluid.layers.data( - name="all_label", - shape=[vocab_size, 1], - dtype="int64", - append_batch_size=False) - emb_all_label = fluid.layers.embedding( + all_label = fluid.data( + name="all_label", shape=[vocab_size, 1], dtype="int64") + emb_all_label = fluid.embedding( input=all_label, size=[vocab_size, hid_size], param_attr="emb") + emb_all_label = fluid.layers.squeeze(input=emb_all_label, axes=[1]) emb_all_label_drop = fluid.layers.dropout( emb_all_label, dropout_prob=dropout, is_test=True) all_pre = fluid.layers.matmul( gru_h0_drop, emb_all_label_drop, transpose_y=True) - pos_label = fluid.layers.data( - name="pos_label", shape=[1], dtype="int64", lod_level=1) + pos_label = fluid.data( + name="pos_label", shape=[None, 1], dtype="int64", lod_level=1) acc = fluid.layers.accuracy(input=all_pre, label=pos_label, k=20) return acc diff --git a/PaddleRec/gru4rec/text2paddle.py b/PaddleRec/gru4rec/text2paddle.py index 563a8cad..47cc8285 100644 --- a/PaddleRec/gru4rec/text2paddle.py +++ b/PaddleRec/gru4rec/text2paddle.py @@ -2,6 +2,11 @@ import sys import six import collections import os +import sys +if six.PY2: + reload(sys) + sys.setdefaultencoding('utf-8') + def word_count(input_file, word_freq=None): """ @@ -25,11 +30,11 @@ def build_dict(min_word_freq=0, train_dir="", test_dir=""): word_freq = collections.defaultdict(int) files = os.listdir(train_dir) for fi in files: - with open(train_dir + '/' + fi, "r") as f: + with open(os.path.join(train_dir, fi), "r", encoding='utf-8') as f: word_freq = word_count(f, word_freq) files = os.listdir(test_dir) for fi in files: - with open(test_dir + '/' + fi, "r") as f: + with open(os.path.join(test_dir, fi), "r", encoding='utf-8') as f: word_freq = word_count(f, word_freq) word_freq = [x for x in six.iteritems(word_freq) if x[1] > min_word_freq] @@ -39,13 +44,16 @@ def build_dict(min_word_freq=0, train_dir="", test_dir=""): return word_idx -def write_paddle(word_idx, train_dir, test_dir, output_train_dir, output_test_dir): +def write_paddle(word_idx, train_dir, test_dir, output_train_dir, + output_test_dir): files = os.listdir(train_dir) if not os.path.exists(output_train_dir): os.mkdir(output_train_dir) for fi in files: - with open(train_dir + '/' + fi, "r") as f: - with open(output_train_dir + '/' + fi, "w") as wf: + with open(os.path.join(train_dir, fi), "r", encoding='utf-8') as f: + with open( + os.path.join(output_train_dir, fi), "w", + encoding='utf-8') as wf: for l in f: l = l.strip().split() l = [word_idx.get(w) for w in l] @@ -57,8 +65,10 @@ def write_paddle(word_idx, train_dir, test_dir, output_train_dir, output_test_di if not os.path.exists(output_test_dir): os.mkdir(output_test_dir) for fi in files: - with open(test_dir + '/' + fi, "r") as f: - with open(output_test_dir + '/' + fi, "w") as wf: + with open(os.path.join(test_dir, fi), "r", encoding='utf-8') as f: + with open( + os.path.join(output_test_dir, fi), "w", + encoding='utf-8') as wf: for l in f: l = l.strip().split() l = [word_idx.get(w) for w in l] @@ -66,9 +76,11 @@ def write_paddle(word_idx, train_dir, test_dir, output_train_dir, output_test_di wf.write(str(w) + " ") wf.write("\n") -def text2paddle(train_dir, test_dir, output_train_dir, output_test_dir, output_vocab): + +def text2paddle(train_dir, test_dir, output_train_dir, output_test_dir, + output_vocab): vocab = build_dict(0, train_dir, test_dir) - with open(output_vocab, "w") as wf: + with open(output_vocab, "w", encoding='utf-8') as wf: wf.write(str(len(vocab)) + "\n") #wf.write(str(vocab)) write_paddle(vocab, train_dir, test_dir, output_train_dir, output_test_dir) @@ -79,4 +91,5 @@ test_dir = sys.argv[2] output_train_dir = sys.argv[3] output_test_dir = sys.argv[4] output_vocab = sys.argv[5] -text2paddle(train_dir, test_dir, output_train_dir, output_test_dir, output_vocab) +text2paddle(train_dir, test_dir, output_train_dir, output_test_dir, + output_vocab) diff --git a/PaddleRec/gru4rec/train.py b/PaddleRec/gru4rec/train.py index b43926b6..686f7a11 100644 --- a/PaddleRec/gru4rec/train.py +++ b/PaddleRec/gru4rec/train.py @@ -58,8 +58,8 @@ def train(): """ do training """ args = parse_args() if args.enable_ce: - fluid.default_startup_program().random_seed = SEED - fluid.default_main_program().random_seed = SEED + fluid.default_startup_program().random_seed = SEED + fluid.default_main_program().random_seed = SEED hid_size = args.hid_size train_dir = args.train_dir vocab_path = args.vocab_path @@ -143,17 +143,16 @@ def train(): if args.use_cuda: gpu_num = device[1] print("kpis\teach_pass_duration_gpu%s\t%s" % - (gpu_num, total_time / epoch_idx)) - print("kpis\ttrain_ppl_gpu%s\t%s" % - (gpu_num, ce_ppl)) + (gpu_num, total_time / epoch_idx)) + print("kpis\ttrain_ppl_gpu%s\t%s" % (gpu_num, ce_ppl)) else: cpu_num = device[1] threads_num = device[2] print("kpis\teach_pass_duration_cpu%s_thread%s\t%s" % - (cpu_num, threads_num, total_time / epoch_idx)) + (cpu_num, threads_num, total_time / epoch_idx)) print("kpis\ttrain_ppl_cpu%s_thread%s\t%s" % - (cpu_num, threads_num, ce_ppl)) - + (cpu_num, threads_num, ce_ppl)) + print("finish training") @@ -166,7 +165,8 @@ def get_device(args): threads_num = os.environ.get('NUM_THREADS', 1) cpu_num = os.environ.get('CPU_NUM', 1) return "cpu", int(cpu_num), int(threads_num) - + if __name__ == "__main__": + utils.check_version() train() diff --git a/PaddleRec/gru4rec/train_sample_neg.py b/PaddleRec/gru4rec/train_sample_neg.py index 26424520..fbb68705 100644 --- a/PaddleRec/gru4rec/train_sample_neg.py +++ b/PaddleRec/gru4rec/train_sample_neg.py @@ -128,4 +128,5 @@ def train(): if __name__ == "__main__": + utils.check_version() train() diff --git a/PaddleRec/gru4rec/utils.py b/PaddleRec/gru4rec/utils.py index 1cd6a313..6996df22 100644 --- a/PaddleRec/gru4rec/utils.py +++ b/PaddleRec/gru4rec/utils.py @@ -6,6 +6,7 @@ import numpy as np import paddle.fluid as fluid import paddle import os +import io def to_lodtensor(data, place): @@ -86,7 +87,7 @@ def to_lodtensor_bpr_test(raw_data, vocab_size, place): def get_vocab_size(vocab_path): - with open(vocab_path, "r") as rf: + with io.open(vocab_path, "r", encoding='utf-8') as rf: line = rf.readline() return int(line.strip()) @@ -110,12 +111,28 @@ def prepare_data(file_dir, batch_size * 20) else: vocab_size = get_vocab_size(vocab_path) - reader = paddle.batch( + reader = fluid.io.batch( test( file_dir, buffer_size, data_type=DataType.SEQ), batch_size) return vocab_size, reader +def check_version(): + """ + Log error and exit when the installed version of paddlepaddle is + not satisfied. + """ + err = "PaddlePaddle version 1.6 or higher is required, " \ + "or a suitable develop version is satisfied as well. \n" \ + "Please make sure the version is good with your code." \ + + try: + fluid.require_version('1.6.0') + except Exception as e: + logger.error(err) + sys.exit(1) + + def sort_batch(reader, batch_size, sort_group_size, drop_last=False): """ Create a batched reader. @@ -170,7 +187,8 @@ def reader_creator(file_dir, n, data_type): def reader(): files = os.listdir(file_dir) for fi in files: - with open(file_dir + '/' + fi, "r") as f: + with io.open( + os.path.join(file_dir, fi), "r", encoding='utf-8') as f: for l in f: if DataType.SEQ == data_type: l = l.strip().split() diff --git a/PaddleRec/multiview_simnet/README.md b/PaddleRec/multiview_simnet/README.md index a3bceaba..1c682eed 100644 --- a/PaddleRec/multiview_simnet/README.md +++ b/PaddleRec/multiview_simnet/README.md @@ -3,6 +3,8 @@ ## Introduction In personalized recommendation scenario, a user often is provided with several items from personalized interest matching model. In real world application, a user may have multiple views of features, say user-id, age, click-history of items, search queries. A item, e.g. news, may also have multiple views of features like news title, news category, images in news and so on. Multi-view Simnet is matching a model that combine users' and items' multiple views of features into one unified model. The model can be used in many industrial product like Baidu's feed news. The model is adapted from the paper A Multi-View Deep Learning(MV-DNN) Approach for Cross Domain User Modeling in Recommendation Systems, WWW 2015. The difference between our model and the MV-DNN is that we also consider multiple feature views of users. +**Now all models in PaddleRec require PaddlePaddle version 1.6 or higher, or suitable develop version.** + We also recommend users to take a look at the [IPython Notebook demo](https://aistudio.baidu.com/aistudio/projectDetail/122294) ## Dataset diff --git a/PaddleRec/multiview_simnet/infer.py b/PaddleRec/multiview_simnet/infer.py index 7b5bb080..e9136588 100644 --- a/PaddleRec/multiview_simnet/infer.py +++ b/PaddleRec/multiview_simnet/infer.py @@ -31,6 +31,22 @@ logger = logging.getLogger("fluid") logger.setLevel(logging.INFO) +def check_version(): + """ + Log error and exit when the installed version of paddlepaddle is + not satisfied. + """ + err = "PaddlePaddle version 1.6 or higher is required, " \ + "or a suitable develop version is satisfied as well. \n" \ + "Please make sure the version is good with your code." \ + + try: + fluid.require_version('1.6.0') + except Exception as e: + logger.error(err) + sys.exit(1) + + def parse_args(): parser = argparse.ArgumentParser("multi-view simnet") parser.add_argument("--train_file", type=str, help="Training file") @@ -116,4 +132,5 @@ def main(): if __name__ == "__main__": + check_version() main() diff --git a/PaddleRec/multiview_simnet/nets.py b/PaddleRec/multiview_simnet/nets.py index fed17784..86d1497b 100644 --- a/PaddleRec/multiview_simnet/nets.py +++ b/PaddleRec/multiview_simnet/nets.py @@ -53,7 +53,6 @@ class CNNEncoder(object): pool_type=self.pool_type, param_attr=self.param_name + ".param", bias_attr=self.param_name + ".bias") - class GrnnEncoder(object): @@ -64,12 +63,11 @@ class GrnnEncoder(object): self.hidden_size = hidden_size def forward(self, emb): - fc0 = nn.fc( - input=emb, - size=self.hidden_size * 3, - param_attr=self.param_name + "_fc.w", - bias_attr=False) - + fc0 = nn.fc(input=emb, + size=self.hidden_size * 3, + param_attr=self.param_name + "_fc.w", + bias_attr=False) + gru_h = nn.dynamic_gru( input=fc0, size=self.hidden_size, @@ -125,34 +123,34 @@ class MultiviewSimnet(object): def train_net(self): # input fields for query, pos_title, neg_title q_slots = [ - io.data( - name="q%d" % i, shape=[1], lod_level=1, dtype='int64') + fluid.data( + name="q%d" % i, shape=[None, 1], lod_level=1, dtype='int64') for i in range(len(self.query_encoders)) ] pt_slots = [ - io.data( - name="pt%d" % i, shape=[1], lod_level=1, dtype='int64') + fluid.data( + name="pt%d" % i, shape=[None, 1], lod_level=1, dtype='int64') for i in range(len(self.title_encoders)) ] nt_slots = [ - io.data( - name="nt%d" % i, shape=[1], lod_level=1, dtype='int64') + fluid.data( + name="nt%d" % i, shape=[None, 1], lod_level=1, dtype='int64') for i in range(len(self.title_encoders)) ] # lookup embedding for each slot q_embs = [ - nn.embedding( + fluid.embedding( input=query, size=self.emb_shape, param_attr="emb") for query in q_slots ] pt_embs = [ - nn.embedding( + fluid.embedding( input=title, size=self.emb_shape, param_attr="emb") for title in pt_slots ] nt_embs = [ - nn.embedding( + fluid.embedding( input=title, size=self.emb_shape, param_attr="emb") for title in nt_slots ] @@ -174,9 +172,18 @@ class MultiviewSimnet(object): nt_concat = nn.concat(nt_encodes) # projection of hidden layer - q_hid = nn.fc(q_concat, size=self.hidden_size, param_attr='q_fc.w', bias_attr='q_fc.b') - pt_hid = nn.fc(pt_concat, size=self.hidden_size, param_attr='t_fc.w', bias_attr='t_fc.b') - nt_hid = nn.fc(nt_concat, size=self.hidden_size, param_attr='t_fc.w', bias_attr='t_fc.b') + q_hid = nn.fc(q_concat, + size=self.hidden_size, + param_attr='q_fc.w', + bias_attr='q_fc.b') + pt_hid = nn.fc(pt_concat, + size=self.hidden_size, + param_attr='t_fc.w', + bias_attr='t_fc.b') + nt_hid = nn.fc(nt_concat, + size=self.hidden_size, + param_attr='t_fc.w', + bias_attr='t_fc.b') # cosine of hidden layers cos_pos = nn.cos_sim(q_hid, pt_hid) @@ -205,23 +212,23 @@ class MultiviewSimnet(object): def pred_net(self, query_fields, pos_title_fields, neg_title_fields): q_slots = [ - io.data( - name="q%d" % i, shape=[1], lod_level=1, dtype='int64') + fluid.data( + name="q%d" % i, shape=[None, 1], lod_level=1, dtype='int64') for i in range(len(self.query_encoders)) ] pt_slots = [ - io.data( - name="pt%d" % i, shape=[1], lod_level=1, dtype='int64') + fluid.data( + name="pt%d" % i, shape=[None, 1], lod_level=1, dtype='int64') for i in range(len(self.title_encoders)) ] # lookup embedding for each slot q_embs = [ - nn.embedding( + fluid.embedding( input=query, size=self.emb_shape, param_attr="emb") for query in q_slots ] pt_embs = [ - nn.embedding( + fluid.embedding( input=title, size=self.emb_shape, param_attr="emb") for title in pt_slots ] @@ -236,8 +243,14 @@ class MultiviewSimnet(object): q_concat = nn.concat(q_encodes) pt_concat = nn.concat(pt_encodes) # projection of hidden layer - q_hid = nn.fc(q_concat, size=self.hidden_size, param_attr='q_fc.w', bias_attr='q_fc.b') - pt_hid = nn.fc(pt_concat, size=self.hidden_size, param_attr='t_fc.w', bias_attr='t_fc.b') + q_hid = nn.fc(q_concat, + size=self.hidden_size, + param_attr='q_fc.w', + bias_attr='q_fc.b') + pt_hid = nn.fc(pt_concat, + size=self.hidden_size, + param_attr='t_fc.w', + bias_attr='t_fc.b') # cosine of hidden layers cos = nn.cos_sim(q_hid, pt_hid) return cos diff --git a/PaddleRec/multiview_simnet/train.py b/PaddleRec/multiview_simnet/train.py index f098fd10..8f4072ad 100644 --- a/PaddleRec/multiview_simnet/train.py +++ b/PaddleRec/multiview_simnet/train.py @@ -88,6 +88,22 @@ def parse_args(): return parser.parse_args() +def check_version(): + """ + Log error and exit when the installed version of paddlepaddle is + not satisfied. + """ + err = "PaddlePaddle version 1.6 or higher is required, " \ + "or a suitable develop version is satisfied as well. \n" \ + "Please make sure the version is good with your code." \ + + try: + fluid.require_version('1.6.0') + except Exception as e: + logger.error(err) + sys.exit(1) + + def start_train(args): if args.enable_ce: SEED = 102 @@ -145,7 +161,7 @@ def start_train(args): # only for ce if args.enable_ce: threads_num, cpu_num = get_cards(args) - epoch_idx = args.epochs + epoch_idx = args.epochs ce_loss = 0 try: ce_loss = ce_info[-2] @@ -153,9 +169,9 @@ def start_train(args): logger.error("ce info error") print("kpis\teach_pass_duration_cpu%s_thread%s\t%s" % - (cpu_num, threads_num, total_time / epoch_idx)) + (cpu_num, threads_num, total_time / epoch_idx)) print("kpis\ttrain_loss_cpu%s_thread%s\t%s" % - (cpu_num, threads_num, ce_loss)) + (cpu_num, threads_num, ce_loss)) def get_cards(args): @@ -170,4 +186,5 @@ def main(): if __name__ == "__main__": + check_version() main() diff --git a/PaddleRec/ssr/README.md b/PaddleRec/ssr/README.md index d0b4dfb4..6abc5240 100644 --- a/PaddleRec/ssr/README.md +++ b/PaddleRec/ssr/README.md @@ -12,6 +12,10 @@ Sequence Semantic Retrieval(SSR) Model shares the similar idea with Multi-Rate D - The idea of SSR is to model a user's personalized interest of an item through matching model structure, and the representation of a news item can be computed online even the news item does not exist in training dataset. - With the representation of news items, we are able to build an vector indexing service online for news prediction and this is the retrieval part of SSR. +## Version +**Now all models in PaddleRec require PaddlePaddle version 1.6 or higher, or suitable develop version.** + + ## Dataset Dataset preprocessing follows the method of [GRU4Rec Project](https://github.com/PaddlePaddle/models/tree/develop/fluid/PaddleRec/gru4rec). Note that you should reuse scripts from GRU4Rec project for data preprocessing. @@ -39,7 +43,7 @@ cpu 单机多卡训练 CPU_NUM=10 python train.py --train_dir train_data --use_cuda 0 --parallel 1 --batch_size 50 --model_dir model_output --num_devices 10 ``` -本地模拟多机训练 +本地模拟多机训练, 不支持windows. ``` bash sh cluster_train.sh ``` diff --git a/PaddleRec/ssr/infer.py b/PaddleRec/ssr/infer.py index 09dee039..3a44fad7 100644 --- a/PaddleRec/ssr/infer.py +++ b/PaddleRec/ssr/infer.py @@ -120,6 +120,7 @@ def infer(args, vocab_size, test_reader): if __name__ == "__main__": + utils.check_version() args = parse_args() start_index = args.start_index last_index = args.last_index diff --git a/PaddleRec/ssr/nets.py b/PaddleRec/ssr/nets.py index 4df23573..6580fb14 100644 --- a/PaddleRec/ssr/nets.py +++ b/PaddleRec/ssr/nets.py @@ -86,16 +86,17 @@ class SequenceSemanticRetrieval(object): return correct def train(self): - user_data = io.data(name="user", shape=[1], dtype="int64", lod_level=1) - pos_item_data = io.data( - name="p_item", shape=[1], dtype="int64", lod_level=1) - neg_item_data = io.data( - name="n_item", shape=[1], dtype="int64", lod_level=1) - user_emb = nn.embedding( + user_data = fluid.data( + name="user", shape=[None, 1], dtype="int64", lod_level=1) + pos_item_data = fluid.data( + name="p_item", shape=[None, 1], dtype="int64", lod_level=1) + neg_item_data = fluid.data( + name="n_item", shape=[None, 1], dtype="int64", lod_level=1) + user_emb = fluid.embedding( input=user_data, size=self.emb_shape, param_attr="emb.item") - pos_item_emb = nn.embedding( + pos_item_emb = fluid.embedding( input=pos_item_data, size=self.emb_shape, param_attr="emb.item") - neg_item_emb = nn.embedding( + neg_item_emb = fluid.embedding( input=neg_item_data, size=self.emb_shape, param_attr="emb.item") user_enc = self.user_encoder.forward(user_emb) pos_item_enc = self.item_encoder.forward(pos_item_emb) diff --git a/PaddleRec/ssr/reader.py b/PaddleRec/ssr/reader.py index 15989fd8..6d73440b 100644 --- a/PaddleRec/ssr/reader.py +++ b/PaddleRec/ssr/reader.py @@ -13,6 +13,7 @@ # limitations under the License. import random +import io class Dataset: @@ -33,7 +34,7 @@ class YoochooseVocab(Vocab): def load(self, filelist): idx = 0 for f in filelist: - with open(f, "r") as fin: + with io.open(f, "r", encoding='utf-8') as fin: for line in fin: group = line.strip().split() for item in group: @@ -64,7 +65,7 @@ class YoochooseDataset(Dataset): def _reader_creator(self, filelist, is_train): def reader(): for f in filelist: - with open(f, 'r') as fin: + with io.open(f, 'r', encoding='utf-8') as fin: line_idx = 0 for line in fin: ids = line.strip().split() diff --git a/PaddleRec/ssr/train.py b/PaddleRec/ssr/train.py index 1c0c9f8c..a3e85d63 100644 --- a/PaddleRec/ssr/train.py +++ b/PaddleRec/ssr/train.py @@ -68,9 +68,9 @@ def get_cards(args): def train(args): if args.enable_ce: - SEED = 102 - fluid.default_startup_program().random_seed = SEED - fluid.default_main_program().random_seed = SEED + SEED = 102 + fluid.default_startup_program().random_seed = SEED + fluid.default_main_program().random_seed = SEED use_cuda = True if args.use_cuda else False parallel = True if args.parallel else False print("use_cuda:", use_cuda, "parallel:", parallel) @@ -136,17 +136,16 @@ def train(args): if args.use_cuda: gpu_num = device[1] print("kpis\teach_pass_duration_gpu%s\t%s" % - (gpu_num, total_time / epoch_idx)) - print("kpis\ttrain_acc_gpu%s\t%s" % - (gpu_num, ce_acc)) + (gpu_num, total_time / epoch_idx)) + print("kpis\ttrain_acc_gpu%s\t%s" % (gpu_num, ce_acc)) else: cpu_num = device[1] threads_num = device[2] print("kpis\teach_pass_duration_cpu%s_thread%s\t%s" % - (cpu_num, threads_num, total_time / epoch_idx)) + (cpu_num, threads_num, total_time / epoch_idx)) print("kpis\ttrain_acc_cpu%s_thread%s\t%s" % - (cpu_num, threads_num, ce_acc)) - + (cpu_num, threads_num, ce_acc)) + def get_device(args): if args.use_cuda: @@ -157,7 +156,7 @@ def get_device(args): threads_num = os.environ.get('NUM_THREADS', 1) cpu_num = os.environ.get('CPU_NUM', 1) return "cpu", int(cpu_num), int(threads_num) - + def main(): args = parse_args() @@ -165,4 +164,5 @@ def main(): if __name__ == "__main__": + utils.check_version() main() diff --git a/PaddleRec/ssr/utils.py b/PaddleRec/ssr/utils.py index 4fe9ef47..65571cb0 100644 --- a/PaddleRec/ssr/utils.py +++ b/PaddleRec/ssr/utils.py @@ -4,10 +4,11 @@ import os import logging import paddle.fluid as fluid import paddle +import io def get_vocab_size(vocab_path): - with open(vocab_path, "r") as rf: + with io.open(vocab_path, "r", encoding='utf-8') as rf: line = rf.readline() return int(line.strip()) @@ -16,7 +17,7 @@ def construct_train_data(file_dir, vocab_path, batch_size): vocab_size = get_vocab_size(vocab_path) files = [file_dir + '/' + f for f in os.listdir(file_dir)] y_data = reader.YoochooseDataset(vocab_size) - train_reader = paddle.batch( + train_reader = fluid.io.batch( paddle.reader.shuffle( y_data.train(files), buf_size=batch_size * 100), batch_size=batch_size) @@ -27,10 +28,26 @@ def construct_test_data(file_dir, vocab_path, batch_size): vocab_size = get_vocab_size(vocab_path) files = [file_dir + '/' + f for f in os.listdir(file_dir)] y_data = reader.YoochooseDataset(vocab_size) - test_reader = paddle.batch(y_data.test(files), batch_size=batch_size) + test_reader = fluid.io.batch(y_data.test(files), batch_size=batch_size) return test_reader, vocab_size +def check_version(): + """ + Log error and exit when the installed version of paddlepaddle is + not satisfied. + """ + err = "PaddlePaddle version 1.6 or higher is required, " \ + "or a suitable develop version is satisfied as well. \n" \ + "Please make sure the version is good with your code." \ + + try: + fluid.require_version('1.6.0') + except Exception as e: + logger.error(err) + sys.exit(1) + + def infer_data(raw_data, place): data = [dat[0] for dat in raw_data] seq_lens = [len(seq) for seq in data] diff --git a/PaddleRec/tagspace/README.md b/PaddleRec/tagspace/README.md index b72a05b8..cd7307f1 100644 --- a/PaddleRec/tagspace/README.md +++ b/PaddleRec/tagspace/README.md @@ -26,6 +26,8 @@ TagSpace模型的介绍可以参阅论文[#TagSpace: Semantic Embeddings from Ha Tagspace模型学习文本及标签的embedding表示，应用于工业级的标签推荐，具体应用场景有feed新闻标签推荐。 +**Now all models in PaddleRec require PaddlePaddle version 1.6 or higher, or suitable develop version.** + 同时推荐用户参考[ IPython Notebook demo](https://aistudio.baidu.com/aistudio/projectDetail/122298) ## 数据下载及预处理 diff --git a/PaddleRec/tagspace/infer.py b/PaddleRec/tagspace/infer.py index e8522b09..66412fc5 100644 --- a/PaddleRec/tagspace/infer.py +++ b/PaddleRec/tagspace/infer.py @@ -71,6 +71,7 @@ def infer(test_reader, vocab_tag, use_cuda, model_path, epoch): if __name__ == "__main__": + utils.check_version() args = parse_args() start_index = args.start_index last_index = args.last_index diff --git a/PaddleRec/tagspace/net.py b/PaddleRec/tagspace/net.py index 797ae634..479d6620 100644 --- a/PaddleRec/tagspace/net.py +++ b/PaddleRec/tagspace/net.py @@ -2,42 +2,53 @@ import paddle.fluid as fluid import paddle.fluid.layers.nn as nn import paddle.fluid.layers.tensor as tensor import paddle.fluid.layers.control_flow as cf -import paddle.fluid.layers.io as io -def network(vocab_text_size, vocab_tag_size, emb_dim=10, hid_dim=1000, win_size=5, margin=0.1, neg_size=5): + +def network(vocab_text_size, + vocab_tag_size, + emb_dim=10, + hid_dim=1000, + win_size=5, + margin=0.1, + neg_size=5): """ network definition """ - text = io.data(name="text", shape=[1], lod_level=1, dtype='int64') - pos_tag = io.data(name="pos_tag", shape=[1], lod_level=1, dtype='int64') - neg_tag = io.data(name="neg_tag", shape=[1], lod_level=1, dtype='int64') - text_emb = nn.embedding( - input=text, size=[vocab_text_size, emb_dim], param_attr="text_emb") - pos_tag_emb = nn.embedding( - input=pos_tag, size=[vocab_tag_size, emb_dim], param_attr="tag_emb") - neg_tag_emb = nn.embedding( - input=neg_tag, size=[vocab_tag_size, emb_dim], param_attr="tag_emb") + text = fluid.data(name="text", shape=[None, 1], lod_level=1, dtype='int64') + pos_tag = fluid.data( + name="pos_tag", shape=[None, 1], lod_level=1, dtype='int64') + neg_tag = fluid.data( + name="neg_tag", shape=[None, 1], lod_level=1, dtype='int64') + text_emb = fluid.embedding( + input=text, size=[vocab_text_size, emb_dim], param_attr="text_emb") + text_emb = fluid.layers.squeeze(input=text_emb, axes=[1]) + pos_tag_emb = fluid.embedding( + input=pos_tag, size=[vocab_tag_size, emb_dim], param_attr="tag_emb") + pos_tag_emb = fluid.layers.squeeze(input=pos_tag_emb, axes=[1]) + neg_tag_emb = fluid.embedding( + input=neg_tag, size=[vocab_tag_size, emb_dim], param_attr="tag_emb") + neg_tag_emb = fluid.layers.squeeze(input=neg_tag_emb, axes=[1]) conv_1d = fluid.nets.sequence_conv_pool( - input=text_emb, - num_filters=hid_dim, - filter_size=win_size, - act="tanh", - pool_type="max", - param_attr="cnn") - text_hid = fluid.layers.fc(input=conv_1d, size=emb_dim, param_attr="text_hid") + input=text_emb, + num_filters=hid_dim, + filter_size=win_size, + act="tanh", + pool_type="max", + param_attr="cnn") + text_hid = fluid.layers.fc(input=conv_1d, + size=emb_dim, + param_attr="text_hid") cos_pos = nn.cos_sim(pos_tag_emb, text_hid) mul_text_hid = fluid.layers.sequence_expand_as(x=text_hid, y=neg_tag_emb) mul_cos_neg = nn.cos_sim(neg_tag_emb, mul_text_hid) - cos_neg_all = fluid.layers.sequence_reshape(input=mul_cos_neg, new_dim=neg_size) + cos_neg_all = fluid.layers.sequence_reshape( + input=mul_cos_neg, new_dim=neg_size) #choose max negtive cosine cos_neg = nn.reduce_max(cos_neg_all, dim=1, keep_dim=True) #calculate hinge loss loss_part1 = nn.elementwise_sub( - tensor.fill_constant_batch_size_like( - input=cos_pos, - shape=[-1, 1], - value=margin, - dtype='float32'), - cos_pos) + tensor.fill_constant_batch_size_like( + input=cos_pos, shape=[-1, 1], value=margin, dtype='float32'), + cos_pos) loss_part2 = nn.elementwise_add(loss_part1, cos_neg) loss_part3 = nn.elementwise_max( tensor.fill_constant_batch_size_like( diff --git a/PaddleRec/tagspace/text2paddle.py b/PaddleRec/tagspace/text2paddle.py index 6aa040c0..b7db212c 100644 --- a/PaddleRec/tagspace/text2paddle.py +++ b/PaddleRec/tagspace/text2paddle.py @@ -2,8 +2,13 @@ import sys import six import collections import os -import csv +import csv import re +import sys +if six.PY2: + reload(sys) + sys.setdefaultencoding('utf-8') + def word_count(column_num, input_file, word_freq=None): """ @@ -13,10 +18,11 @@ def word_count(column_num, input_file, word_freq=None): word_freq = collections.defaultdict(int) data_file = csv.reader(input_file) for row in data_file: - for w in re.split(r'\W+',row[column_num].strip()): - word_freq[w]+= 1 + for w in re.split(r'\W+', row[column_num].strip()): + word_freq[w] += 1 return word_freq + def build_dict(column_num=2, min_word_freq=0, train_dir="", test_dir=""): """ Build a word dictionary from the corpus, Keys of the dictionary are words, @@ -25,11 +31,11 @@ def build_dict(column_num=2, min_word_freq=0, train_dir="", test_dir=""): word_freq = collections.defaultdict(int) files = os.listdir(train_dir) for fi in files: - with open(train_dir + '/' + fi, "r") as f: + with open(os.path.join(train_dir, fi), "r", encoding='utf-8') as f: word_freq = word_count(column_num, f, word_freq) files = os.listdir(test_dir) for fi in files: - with open(test_dir + '/' + fi, "r") as f: + with open(os.path.join(test_dir, fi), "r", encoding='utf-8') as f: word_freq = word_count(column_num, f, word_freq) word_freq = [x for x in six.iteritems(word_freq) if x[1] > min_word_freq] @@ -39,13 +45,16 @@ def build_dict(column_num=2, min_word_freq=0, train_dir="", test_dir=""): return word_idx -def write_paddle(text_idx, tag_idx, train_dir, test_dir, output_train_dir, output_test_dir): +def write_paddle(text_idx, tag_idx, train_dir, test_dir, output_train_dir, + output_test_dir): files = os.listdir(train_dir) if not os.path.exists(output_train_dir): os.mkdir(output_train_dir) for fi in files: - with open(train_dir + '/' + fi, "r") as f: - with open(output_train_dir + '/' + fi, "w") as wf: + with open(os.path.join(train_dir, fi), "r", encoding='utf-8') as f: + with open( + os.path.join(output_train_dir, fi), "w", + encoding='utf-8') as wf: data_file = csv.reader(f) for row in data_file: tag_raw = re.split(r'\W+', row[0].strip()) @@ -61,8 +70,10 @@ def write_paddle(text_idx, tag_idx, train_dir, test_dir, output_train_dir, outpu if not os.path.exists(output_test_dir): os.mkdir(output_test_dir) for fi in files: - with open(test_dir + '/' + fi, "r") as f: - with open(output_test_dir + '/' + fi, "w") as wf: + with open(os.path.join(test_dir, fi), "r", encoding='utf-8') as f: + with open( + os.path.join(output_test_dir, fi), "w", + encoding='utf-8') as wf: data_file = csv.reader(f) for row in data_file: tag_raw = re.split(r'\W+', row[0].strip()) @@ -74,18 +85,21 @@ def write_paddle(text_idx, tag_idx, train_dir, test_dir, output_train_dir, outpu wf.write(str(w) + " ") wf.write("\n") -def text2paddle(train_dir, test_dir, output_train_dir, output_test_dir, output_vocab_text, output_vocab_tag): + +def text2paddle(train_dir, test_dir, output_train_dir, output_test_dir, + output_vocab_text, output_vocab_tag): print("start constuct word dict") vocab_text = build_dict(2, 0, train_dir, test_dir) - with open(output_vocab_text, "w") as wf: + with open(output_vocab_text, "w", encoding='utf-8') as wf: wf.write(str(len(vocab_text)) + "\n") vocab_tag = build_dict(0, 0, train_dir, test_dir) - with open(output_vocab_tag, "w") as wf: + with open(output_vocab_tag, "w", encoding='utf-8') as wf: wf.write(str(len(vocab_tag)) + "\n") print("construct word dict done\n") - write_paddle(vocab_text, vocab_tag, train_dir, test_dir, output_train_dir, output_test_dir) + write_paddle(vocab_text, vocab_tag, train_dir, test_dir, output_train_dir, + output_test_dir) train_dir = sys.argv[1] @@ -94,4 +108,5 @@ output_train_dir = sys.argv[3] output_test_dir = sys.argv[4] output_vocab_text = sys.argv[5] output_vocab_tag = sys.argv[6] -text2paddle(train_dir, test_dir, output_train_dir, output_test_dir, output_vocab_text, output_vocab_tag) +text2paddle(train_dir, test_dir, output_train_dir, output_test_dir, + output_vocab_text, output_vocab_tag) diff --git a/PaddleRec/tagspace/train.py b/PaddleRec/tagspace/train.py index 419bb1c4..da3563e0 100644 --- a/PaddleRec/tagspace/train.py +++ b/PaddleRec/tagspace/train.py @@ -56,8 +56,8 @@ def train(): """ do training """ args = parse_args() if args.enable_ce: - fluid.default_startup_program().random_seed = SEED - fluid.default_main_program().random_seed = SEED + fluid.default_startup_program().random_seed = SEED + fluid.default_main_program().random_seed = SEED train_dir = args.train_dir vocab_text_path = args.vocab_text_path vocab_tag_path = args.vocab_tag_path @@ -114,7 +114,8 @@ def train(): "neg_tag": lod_neg_tag }, fetch_list=[avg_cost.name, correct.name]) - ce_info.append(float(np.sum(correct_val)) / (args.num_devices * batch_size)) + ce_info.append( + float(np.sum(correct_val)) / (args.num_devices * batch_size)) if batch_id % args.print_batch == 0: print("TRAIN --> pass: {} batch_num: {} avg_cost: {}, acc: {}" .format(pass_idx, (batch_id + 10) * batch_size, @@ -128,8 +129,7 @@ def train(): save_dir = "%s/epoch_%d" % (model_dir, epoch_idx) feed_var_names = ["text", "pos_tag"] fetch_vars = [cos_pos] - fluid.io.save_inference_model(save_dir, feed_var_names, fetch_vars, - exe) + fluid.io.save_inference_model(save_dir, feed_var_names, fetch_vars, exe) # only for ce if args.enable_ce: ce_acc = 0 @@ -142,17 +142,16 @@ def train(): if args.use_cuda: gpu_num = device[1] print("kpis\teach_pass_duration_gpu%s\t%s" % - (gpu_num, total_time / epoch_idx)) - print("kpis\ttrain_acc_gpu%s\t%s" % - (gpu_num, ce_acc)) + (gpu_num, total_time / epoch_idx)) + print("kpis\ttrain_acc_gpu%s\t%s" % (gpu_num, ce_acc)) else: cpu_num = device[1] threads_num = device[2] print("kpis\teach_pass_duration_cpu%s_thread%s\t%s" % - (cpu_num, threads_num, total_time / epoch_idx)) + (cpu_num, threads_num, total_time / epoch_idx)) print("kpis\ttrain_acc_cpu%s_thread%s\t%s" % - (cpu_num, threads_num, ce_acc)) - + (cpu_num, threads_num, ce_acc)) + print("finish training") @@ -165,7 +164,8 @@ def get_device(args): threads_num = os.environ.get('NUM_THREADS', 1) cpu_num = os.environ.get('CPU_NUM', 1) return "cpu", int(cpu_num), int(threads_num) - + if __name__ == "__main__": + utils.check_version() train() diff --git a/PaddleRec/tagspace/utils.py b/PaddleRec/tagspace/utils.py index f5b7e647..7ae71249 100644 --- a/PaddleRec/tagspace/utils.py +++ b/PaddleRec/tagspace/utils.py @@ -8,6 +8,11 @@ import numpy as np import paddle.fluid as fluid import paddle import csv +import io +if six.PY2: + reload(sys) + sys.setdefaultencoding('utf-8') + def to_lodtensor(data, place): """ convert to LODtensor """ @@ -24,12 +29,29 @@ def to_lodtensor(data, place): res.set_lod([lod]) return res + def get_vocab_size(vocab_path): - with open(vocab_path, "r") as rf: + with io.open(vocab_path, "r") as rf: line = rf.readline() return int(line.strip()) +def check_version(): + """ + Log error and exit when the installed version of paddlepaddle is + not satisfied. + """ + err = "PaddlePaddle version 1.6 or higher is required, " \ + "or a suitable develop version is satisfied as well. \n" \ + "Please make sure the version is good with your code." \ + + try: + fluid.require_version('1.6.0') + except Exception as e: + logger.error(err) + sys.exit(1) + + def prepare_data(file_dir, vocab_text_path, vocab_tag_path, @@ -45,19 +67,25 @@ def prepare_data(file_dir, reader = sort_batch( paddle.reader.shuffle( train( - file_dir, vocab_tag_size, neg_size, - buffer_size, data_type=DataType.SEQ), + file_dir, + vocab_tag_size, + neg_size, + buffer_size, + data_type=DataType.SEQ), buf_size=buffer_size), - batch_size, batch_size * 20) + batch_size, + batch_size * 20) else: vocab_tag_size = get_vocab_size(vocab_tag_path) vocab_text_size = 0 reader = sort_batch( test( file_dir, vocab_tag_size, buffer_size, data_type=DataType.SEQ), - batch_size, batch_size * 20) + batch_size, + batch_size * 20) return vocab_text_size, vocab_tag_size, reader + def sort_batch(reader, batch_size, sort_group_size, drop_last=False): """ Create a batched reader. @@ -107,11 +135,13 @@ def sort_batch(reader, batch_size, sort_group_size, drop_last=False): class DataType(object): SEQ = 2 + def train_reader_creator(file_dir, tag_size, neg_size, n, data_type): def reader(): files = os.listdir(file_dir) for fi in files: - with open(file_dir + '/' + fi, "r") as f: + with io.open( + os.path.join(file_dir, fi), "r", encoding='utf-8') as f: for l in f: l = l.strip().split(",") pos_index = int(l[0]) @@ -123,7 +153,7 @@ def train_reader_creator(file_dir, tag_size, neg_size, n, data_type): max_iter = 100 now_iter = 0 sum_n = 0 - while(sum_n < neg_size) : + while (sum_n < neg_size): now_iter += 1 if now_iter > max_iter: print("error : only one class") @@ -135,13 +165,16 @@ def train_reader_creator(file_dir, tag_size, neg_size, n, data_type): sum_n += 1 if n > 0 and len(text) > n: continue yield text, pos_tag, neg_tag + return reader + def test_reader_creator(file_dir, tag_size, n, data_type): def reader(): files = os.listdir(file_dir) for fi in files: - with open(file_dir + '/' + fi, "r") as f: + with io.open( + os.path.join(file_dir, fi), "r", encoding='utf-8') as f: for l in f: l = l.strip().split(",") pos_index = int(l[0]) @@ -153,11 +186,13 @@ def test_reader_creator(file_dir, tag_size, n, data_type): tag = [] tag.append(ii) yield text, tag, pos_tag + return reader def train(train_dir, tag_size, neg_size, n, data_type=DataType.SEQ): return train_reader_creator(train_dir, tag_size, neg_size, n, data_type) + def test(test_dir, tag_size, n, data_type=DataType.SEQ): return test_reader_creator(test_dir, tag_size, n, data_type) diff --git a/PaddleRec/word2vec/README.md b/PaddleRec/word2vec/README.md index 724e7bc1..581c81ac 100644 --- a/PaddleRec/word2vec/README.md +++ b/PaddleRec/word2vec/README.md @@ -20,6 +20,8 @@ ## 介绍 本例实现了skip-gram模式的word2vector模型。 +**目前模型库下模型均要求使用PaddlePaddle 1.6及以上版本或适当的develop版本。** + 同时推荐用户参考[ IPython Notebook demo](https://aistudio.baidu.com/aistudio/projectDetail/124377) ## 数据下载 @@ -36,7 +38,7 @@ mv 1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tok ```bash mkdir data -wget https://paddlerec.bj.bcebos.com/word2vec/1-billion-word-language-modeling-benchmark-r13output.tar +wget --no-check-certificate https://paddlerec.bj.bcebos.com/word2vec/1-billion-word-language-modeling-benchmark-r13output.tar tar xvf 1-billion-word-language-modeling-benchmark-r13output.tar mv 1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/ data/ ``` @@ -45,7 +47,7 @@ mv 1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tok ```bash mkdir data -wget https://paddlerec.bj.bcebos.com/word2vec/text.tar +wget --no-check-certificate https://paddlerec.bj.bcebos.com/word2vec/text.tar tar xvf text.tar mv text data/ ``` @@ -95,7 +97,7 @@ python train.py -h OPENBLAS_NUM_THREADS=1 CPU_NUM=5 python train.py --train_data_dir data/convert_text8 --dict_path data/test_build_dict --num_passes 10 --batch_size 100 --model_output_dir v1_cpu5_b100_lr1dir --base_lr 1.0 --print_batch 1000 --with_speed --is_sparse ``` -本地单机模拟多机训练 +本地单机模拟多机训练, 目前暂不支持windows。 ```bash sh cluster_train.sh @@ -106,9 +108,9 @@ sh cluster_train.sh ```bash #全量数据集测试集 -wget https://paddlerec.bj.bcebos.com/word2vec/test_dir.tar +wget --no-check-certificate https://paddlerec.bj.bcebos.com/word2vec/test_dir.tar #样本数据集测试集 -wget https://paddlerec.bj.bcebos.com/word2vec/test_mid_dir.tar +wget --no-check-certificate https://paddlerec.bj.bcebos.com/word2vec/test_mid_dir.tar ``` 预测命令，注意词典名称需要加后缀"_word_to_id_", 此文件是预处理阶段生成的。 diff --git a/PaddleRec/word2vec/infer.py b/PaddleRec/word2vec/infer.py index 1b329002..32f65d17 100644 --- a/PaddleRec/word2vec/infer.py +++ b/PaddleRec/word2vec/infer.py @@ -10,6 +10,9 @@ import paddle.fluid as fluid import paddle import net import utils +if six.PY2: + reload(sys) + sys.setdefaultencoding('utf-8') def parse_args(): @@ -76,15 +79,12 @@ def infer_epoch(args, vocab_size, test_reader, use_cuda, i2w): for data in test_reader(): step_id += 1 b_size = len([dat[0] for dat in data]) - wa = np.array( - [dat[0] for dat in data]).astype("int64").reshape( - b_size, 1) - wb = np.array( - [dat[1] for dat in data]).astype("int64").reshape( - b_size, 1) - wc = np.array( - [dat[2] for dat in data]).astype("int64").reshape( - b_size, 1) + wa = np.array([dat[0] for dat in data]).astype( + "int64").reshape(b_size) + wb = np.array([dat[1] for dat in data]).astype( + "int64").reshape(b_size) + wc = np.array([dat[2] for dat in data]).astype( + "int64").reshape(b_size) label = [dat[3] for dat in data] input_word = [dat[4] for dat in data] @@ -93,9 +93,8 @@ def infer_epoch(args, vocab_size, test_reader, use_cuda, i2w): "analogy_a": wa, "analogy_b": wb, "analogy_c": wc, - "all_label": - np.arange(vocab_size).reshape( - vocab_size, 1).astype("int64"), + "all_label": np.arange(vocab_size) + .reshape(vocab_size).astype("int64"), }, fetch_list=[pred.name, values], return_numpy=False) @@ -143,15 +142,12 @@ def infer_step(args, vocab_size, test_reader, use_cuda, i2w): for data in test_reader(): step_id += 1 b_size = len([dat[0] for dat in data]) - wa = np.array( - [dat[0] for dat in data]).astype("int64").reshape( - b_size, 1) - wb = np.array( - [dat[1] for dat in data]).astype("int64").reshape( - b_size, 1) - wc = np.array( - [dat[2] for dat in data]).astype("int64").reshape( - b_size, 1) + wa = np.array([dat[0] for dat in data]).astype( + "int64").reshape(b_size) + wb = np.array([dat[1] for dat in data]).astype( + "int64").reshape(b_size) + wc = np.array([dat[2] for dat in data]).astype( + "int64").reshape(b_size) label = [dat[3] for dat in data] input_word = [dat[4] for dat in data] @@ -162,7 +158,7 @@ def infer_step(args, vocab_size, test_reader, use_cuda, i2w): "analogy_b": wb, "analogy_c": wc, "all_label": - np.arange(vocab_size).reshape(vocab_size, 1), + np.arange(vocab_size).reshape(vocab_size), }, fetch_list=[pred.name, values], return_numpy=False) @@ -185,6 +181,7 @@ def infer_step(args, vocab_size, test_reader, use_cuda, i2w): if __name__ == "__main__": + utils.check_version() args = parse_args() start_index = args.start_index last_index = args.last_index diff --git a/PaddleRec/word2vec/net.py b/PaddleRec/word2vec/net.py index ab2abbc7..b8379b66 100644 --- a/PaddleRec/word2vec/net.py +++ b/PaddleRec/word2vec/net.py @@ -23,10 +23,10 @@ import paddle.fluid as fluid def skip_gram_word2vec(dict_size, embedding_size, is_sparse=False, neg_num=5): datas = [] - input_word = fluid.layers.data(name="input_word", shape=[1], dtype='int64') - true_word = fluid.layers.data(name='true_label', shape=[1], dtype='int64') - neg_word = fluid.layers.data( - name="neg_label", shape=[neg_num], dtype='int64') + input_word = fluid.data(name="input_word", shape=[None, 1], dtype='int64') + true_word = fluid.data(name='true_label', shape=[None, 1], dtype='int64') + neg_word = fluid.data( + name="neg_label", shape=[None, neg_num], dtype='int64') datas.append(input_word) datas.append(true_word) @@ -37,7 +37,7 @@ def skip_gram_word2vec(dict_size, embedding_size, is_sparse=False, neg_num=5): words = fluid.layers.read_file(py_reader) init_width = 0.5 / embedding_size - input_emb = fluid.layers.embedding( + input_emb = fluid.embedding( input=words[0], is_sparse=is_sparse, size=[dict_size, embedding_size], @@ -45,33 +45,31 @@ def skip_gram_word2vec(dict_size, embedding_size, is_sparse=False, neg_num=5): name='emb', initializer=fluid.initializer.Uniform(-init_width, init_width))) - true_emb_w = fluid.layers.embedding( + true_emb_w = fluid.embedding( input=words[1], is_sparse=is_sparse, size=[dict_size, embedding_size], param_attr=fluid.ParamAttr( name='emb_w', initializer=fluid.initializer.Constant(value=0.0))) - true_emb_b = fluid.layers.embedding( + true_emb_b = fluid.embedding( input=words[1], is_sparse=is_sparse, size=[dict_size, 1], param_attr=fluid.ParamAttr( name='emb_b', initializer=fluid.initializer.Constant(value=0.0))) - neg_word_reshape = fluid.layers.reshape(words[2], shape=[-1, 1]) - neg_word_reshape.stop_gradient = True + input_emb = fluid.layers.squeeze(input=input_emb, axes=[1]) + true_emb_w = fluid.layers.squeeze(input=true_emb_w, axes=[1]) + true_emb_b = fluid.layers.squeeze(input=true_emb_b, axes=[1]) - neg_emb_w = fluid.layers.embedding( - input=neg_word_reshape, + neg_emb_w = fluid.embedding( + input=words[2], is_sparse=is_sparse, size=[dict_size, embedding_size], param_attr=fluid.ParamAttr( name='emb_w', learning_rate=1.0)) - - neg_emb_w_re = fluid.layers.reshape( - neg_emb_w, shape=[-1, neg_num, embedding_size]) - neg_emb_b = fluid.layers.embedding( - input=neg_word_reshape, + neg_emb_b = fluid.embedding( + input=words[2], is_sparse=is_sparse, size=[dict_size, 1], param_attr=fluid.ParamAttr( @@ -86,8 +84,7 @@ def skip_gram_word2vec(dict_size, embedding_size, is_sparse=False, neg_num=5): true_emb_b) input_emb_re = fluid.layers.reshape( input_emb, shape=[-1, 1, embedding_size]) - neg_matmul = fluid.layers.matmul( - input_emb_re, neg_emb_w_re, transpose_y=True) + neg_matmul = fluid.layers.matmul(input_emb_re, neg_emb_w, transpose_y=True) neg_matmul_re = fluid.layers.reshape(neg_matmul, shape=[-1, neg_num]) neg_logits = fluid.layers.elementwise_add(neg_matmul_re, neg_emb_b_vec) #nce loss @@ -111,22 +108,18 @@ def skip_gram_word2vec(dict_size, embedding_size, is_sparse=False, neg_num=5): def infer_network(vocab_size, emb_size): - analogy_a = fluid.layers.data(name="analogy_a", shape=[1], dtype='int64') - analogy_b = fluid.layers.data(name="analogy_b", shape=[1], dtype='int64') - analogy_c = fluid.layers.data(name="analogy_c", shape=[1], dtype='int64') - all_label = fluid.layers.data( - name="all_label", - shape=[vocab_size, 1], - dtype='int64', - append_batch_size=False) - emb_all_label = fluid.layers.embedding( + analogy_a = fluid.data(name="analogy_a", shape=[None], dtype='int64') + analogy_b = fluid.data(name="analogy_b", shape=[None], dtype='int64') + analogy_c = fluid.data(name="analogy_c", shape=[None], dtype='int64') + all_label = fluid.data(name="all_label", shape=[vocab_size], dtype='int64') + emb_all_label = fluid.embedding( input=all_label, size=[vocab_size, emb_size], param_attr="emb") - emb_a = fluid.layers.embedding( + emb_a = fluid.embedding( input=analogy_a, size=[vocab_size, emb_size], param_attr="emb") - emb_b = fluid.layers.embedding( + emb_b = fluid.embedding( input=analogy_b, size=[vocab_size, emb_size], param_attr="emb") - emb_c = fluid.layers.embedding( + emb_c = fluid.embedding( input=analogy_c, size=[vocab_size, emb_size], param_attr="emb") target = fluid.layers.elementwise_add( fluid.layers.elementwise_sub(emb_b, emb_a), emb_c) diff --git a/PaddleRec/word2vec/preprocess.py b/PaddleRec/word2vec/preprocess.py index 1d5ad03c..030ac0be 100644 --- a/PaddleRec/word2vec/preprocess.py +++ b/PaddleRec/word2vec/preprocess.py @@ -6,6 +6,10 @@ import six import argparse import io import math +import sys +if six.PY2: + reload(sys) + sys.setdefaultencoding('utf-8') prog = re.compile("[^a-z ]", flags=0) @@ -110,10 +114,14 @@ def filter_corpus(args): if not os.path.exists(args.output_corpus_dir): os.makedirs(args.output_corpus_dir) for file in os.listdir(args.input_corpus_dir): - with io.open(args.output_corpus_dir + '/convert_' + file, "w") as wf: + with io.open( + os.path.join(args.output_corpus_dir, 'convert_' + file), + "w", + encoding='utf-8') as wf: with io.open( - args.input_corpus_dir + '/' + file, encoding='utf-8') as rf: - print(args.input_corpus_dir + '/' + file) + os.path.join(args.input_corpus_dir, file), + encoding='utf-8') as rf: + print(os.path.join(args.input_corpus_dir, file)) for line in rf: signal = False line = text_strip(line) diff --git a/PaddleRec/word2vec/train.py b/PaddleRec/word2vec/train.py index 430ec132..087c9b1d 100644 --- a/PaddleRec/word2vec/train.py +++ b/PaddleRec/word2vec/train.py @@ -12,6 +12,12 @@ import six import reader from net import skip_gram_word2vec +import utils +import sys +if six.PY2: + reload(sys) + sys.setdefaultencoding('utf-8') + logging.basicConfig(format='%(asctime)s - %(levelname)s - %(message)s') logger = logging.getLogger("fluid") logger.setLevel(logging.INFO) @@ -224,5 +230,6 @@ def train(args): if __name__ == '__main__': + utils.check_version() args = parse_args() train(args) diff --git a/PaddleRec/word2vec/utils.py b/PaddleRec/word2vec/utils.py index 01cd04e4..c09e30d7 100644 --- a/PaddleRec/word2vec/utils.py +++ b/PaddleRec/word2vec/utils.py @@ -7,12 +7,13 @@ import paddle.fluid as fluid import paddle import os import preprocess +import io def BuildWord_IdMap(dict_path): word_to_id = dict() id_to_word = dict() - with open(dict_path, 'r') as f: + with io.open(dict_path, 'r', encoding='utf-8') as f: for line in f: word_to_id[line.split(' ')[0]] = int(line.split(' ')[1]) id_to_word[int(line.split(' ')[1])] = line.split(' ')[0] @@ -22,10 +23,26 @@ def BuildWord_IdMap(dict_path): def prepare_data(file_dir, dict_path, batch_size): w2i, i2w = BuildWord_IdMap(dict_path) vocab_size = len(i2w) - reader = paddle.batch(test(file_dir, w2i), batch_size) + reader = fluid.io.batch(test(file_dir, w2i), batch_size) return vocab_size, reader, i2w +def check_version(): + """ + Log error and exit when the installed version of paddlepaddle is + not satisfied. + """ + err = "PaddlePaddle version 1.6 or higher is required, " \ + "or a suitable develop version is satisfied as well. \n" \ + "Please make sure the version is good with your code." \ + + try: + fluid.require_version('1.6.0') + except Exception as e: + logger.error(err) + sys.exit(1) + + def native_to_unicode(s): if _is_unicode(s): return s @@ -75,7 +92,8 @@ def reader_creator(file_dir, word_to_id): def reader(): files = os.listdir(file_dir) for fi in files: - with open(file_dir + '/' + fi, "r") as f: + with io.open( + os.path.join(file_dir, fi), "r", encoding='utf-8') as f: for line in f: if ':' in line: pass -- GitLab