-## 使用教程 -### 训练&预测 +## 使用教程(快速开始) +### 训练 ```shell python -m paddlerec.run -m paddlerec.models.match.dssm # dssm python -m paddlerec.run -m paddlerec.models.match.multiview-simnet # multiview-simnet ``` + +### 预测 +```shell +# 修改对应模型的config.yaml, workspace配置为当前目录的绝对路径 +# 修改对应模型的config.yaml，mode配置infer_runner +# 示例: mode: train_runner -> mode: infer_runner +# infer_runner中 class配置为 class: single_infer +# 修改phase阶段为infer的配置，参照config注释 + +# 修改完config.yaml后 执行: +python -m paddlerec.run -m ./config.yaml # 以dssm为例 +``` diff --git a/models/recall/gnn/config.yaml b/models/recall/gnn/config.yaml index d200ddc37083ab68b1456ce7fd7bef4fb9870985..f4d5b1efdd213c7ef14af170ab124426b5bc14c6 100755 --- a/models/recall/gnn/config.yaml +++ b/models/recall/gnn/config.yaml @@ -36,17 +36,17 @@ hyper_parameters: decay_steps: 3 decay_rate: 0.1 l2: 0.00001 - sparse_feature_nums: 43098 + sparse_feature_number: 43098 sparse_feature_dim: 100 corpus_size: 719470 gnn_propogation_steps: 1 # select runner by name -mode: runner1 +mode: train_runner # config of each runner. # runner is a kind of paddle training class, which wraps the train/infer process. runner: -- name: runner1 +- name: train_runner class: single_train # num of epochs epochs: 2 @@ -60,7 +60,7 @@ runner: save_inference_fetch_varnames: [] # fetch vars of save inference init_model_path: "" # load model path fetch_period: 10 -- name: runner2 +- name: infer_runner class: single_infer # num of epochs epochs: 1 diff --git a/models/recall/gnn/raw_data/convert_data.py b/models/recall/gnn/data/convert_data.py similarity index 100% rename from models/recall/gnn/raw_data/convert_data.py rename to models/recall/gnn/data/convert_data.py diff --git a/models/recall/gnn/raw_data/download.py b/models/recall/gnn/data/download.py similarity index 100% rename from models/recall/gnn/raw_data/download.py rename to models/recall/gnn/data/download.py diff --git a/models/recall/gnn/raw_data/preprocess.py b/models/recall/gnn/data/preprocess.py similarity index 100% rename from models/recall/gnn/raw_data/preprocess.py rename to models/recall/gnn/data/preprocess.py diff --git a/models/recall/gnn/data_process.sh b/models/recall/gnn/data_prepare.sh similarity index 82% rename from models/recall/gnn/data_process.sh rename to models/recall/gnn/data_prepare.sh index fc7ed827e0368c59cab8134d22f78e2200980f18..00a3dcebb01f33424ed9e9517967e5cb613bee81 100755 --- a/models/recall/gnn/data_process.sh +++ b/models/recall/gnn/data_prepare.sh @@ -17,7 +17,7 @@ set -e echo "begin to download data" -cd raw_data && python download.py +cd data && python download.py mkdir diginetica python preprocess.py --dataset diginetica @@ -26,8 +26,10 @@ python convert_data.py --data_dir diginetica cat diginetica/train.txt | wc -l >> diginetica/config.txt -mkdir train_data -mv diginetica/train.txt train_data +rm -rf train && mkdir train +mv diginetica/train.txt train -mkdir test_data -mv diginetica/test.txt test_data +rm -rf test && mkdir test +mv diginetica/test.txt test + +mv diginetica/config.txt ./config.txt diff --git a/models/recall/gnn/model.py b/models/recall/gnn/model.py index 6e7d2ab5de4b31d3154e4a2c27aabdd1a7374555..74ffd7866d92824a0d23aead5bed3d143727381b 100755 --- a/models/recall/gnn/model.py +++ b/models/recall/gnn/model.py @@ -36,7 +36,7 @@ class Model(ModelBase): self.l2 = envs.get_global_env("hyper_parameters.optimizer.l2") self.dict_size = envs.get_global_env( - "hyper_parameters.sparse_feature_nums") + "hyper_parameters.sparse_feature_number") self.corpus_size = envs.get_global_env("hyper_parameters.corpus_size") self.train_batch_size = envs.get_global_env( diff --git a/models/recall/word2vec/config.yaml b/models/recall/word2vec/config.yaml index 7a1452a7a3e7dc31f381a05ec806386179c39b67..e2785555c32d3a2300c36a2eba6e8b030fc172b9 100755 --- a/models/recall/word2vec/config.yaml +++ b/models/recall/word2vec/config.yaml @@ -35,18 +35,18 @@ hyper_parameters: decay_rate: 0.999 class: sgd strategy: async - sparse_feature_number: 85 + sparse_feature_number: 354051 sparse_feature_dim: 300 with_shuffle_batch: False neg_num: 5 window_size: 5 # select runner by name -mode: runner1 +mode: train_runner # config of each runner. # runner is a kind of paddle training class, which wraps the train/infer process. runner: -- name: runner1 +- name: train_runner class: single_train # num of epochs epochs: 2 @@ -60,7 +60,7 @@ runner: save_inference_fetch_varnames: [] # fetch vars of save inference init_model_path: "" # load model path fetch_period: 10 -- name: runner2 +- name: infer_runner class: single_infer # num of epochs epochs: 1 diff --git a/models/recall/word2vec/model.py b/models/recall/word2vec/model.py index 16dc94f47730484c0ffcfab998b633e45f185953..5822c90fa8b91342cb6d44d1e5cb1781ef96e9cd 100755 --- a/models/recall/word2vec/model.py +++ b/models/recall/word2vec/model.py @@ -70,13 +70,14 @@ class Model(ModelBase): def embedding_layer(input, table_name, + emb_dim, initializer_instance=None, squeeze=False): emb = fluid.embedding( input=input, is_sparse=True, is_distributed=self.is_distributed, - size=[self.sparse_feature_number, self.sparse_feature_dim], + size=[self.sparse_feature_number, emb_dim], param_attr=fluid.ParamAttr( name=table_name, initializer=initializer_instance), ) if squeeze: @@ -84,12 +85,16 @@ class Model(ModelBase): else: return emb - init_width = 1.0 / self.sparse_feature_dim + init_width = 0.5 / self.sparse_feature_dim emb_initializer = fluid.initializer.Uniform(-init_width, init_width) emb_w_initializer = fluid.initializer.Constant(value=0.0) - input_emb = embedding_layer(inputs[0], "emb", emb_initializer, True) - true_emb_w = embedding_layer(inputs[1], "emb_w", emb_w_initializer, + input_emb = embedding_layer(inputs[0], "emb", self.sparse_feature_dim, + emb_initializer, True) + true_emb_w = embedding_layer(inputs[1], "emb_w", + self.sparse_feature_dim, + emb_w_initializer, True) + true_emb_b = embedding_layer(inputs[1], "emb_b", 1, emb_w_initializer, True) if self.with_shuffle_batch: @@ -102,34 +107,74 @@ class Model(ModelBase): neg_emb_w = fluid.layers.reshape( neg_emb_w_concat, shape=[-1, self.neg_num, self.sparse_feature_dim]) + + neg_emb_b_list = [] + for i in range(self.neg_num): + neg_emb_b_list.append( + fluid.contrib.layers.shuffle_batch( + true_emb_b)) # shuffle true_word + neg_emb_b = fluid.layers.concat(neg_emb_b_list, axis=0) + neg_emb_b_vec = fluid.layers.reshape( + neg_emb_b, shape=[-1, self.neg_num]) else: - neg_emb_w = embedding_layer(inputs[2], "emb_w", emb_w_initializer) - true_logits = fluid.layers.reduce_sum( - fluid.layers.elementwise_mul(input_emb, true_emb_w), - dim=1, - keep_dim=True) + neg_emb_w = embedding_layer( + inputs[2], "emb_w", self.sparse_feature_dim, emb_w_initializer) + neg_emb_b = embedding_layer(inputs[2], "emb_b", 1, + emb_w_initializer) + neg_emb_b_vec = fluid.layers.reshape( + neg_emb_b, shape=[-1, self.neg_num]) + + true_logits = fluid.layers.elementwise_add( + fluid.layers.reduce_sum( + fluid.layers.elementwise_mul(input_emb, true_emb_w), + dim=1, + keep_dim=True), + true_emb_b) input_emb_re = fluid.layers.reshape( input_emb, shape=[-1, 1, self.sparse_feature_dim]) neg_matmul = fluid.layers.matmul( input_emb_re, neg_emb_w, transpose_y=True) - neg_logits = fluid.layers.reshape(neg_matmul, shape=[-1, 1]) + neg_matmul_re = fluid.layers.reshape( + neg_matmul, shape=[-1, self.neg_num]) + neg_logits = fluid.layers.elementwise_add(neg_matmul_re, neg_emb_b_vec) + #nce loss - logits = fluid.layers.concat([true_logits, neg_logits], axis=0) label_ones = fluid.layers.fill_constant( shape=[fluid.layers.shape(true_logits)[0], 1], value=1.0, dtype='float32') label_zeros = fluid.layers.fill_constant( - shape=[fluid.layers.shape(neg_logits)[0], 1], + shape=[fluid.layers.shape(true_logits)[0], self.neg_num], value=0.0, dtype='float32') - label = fluid.layers.concat([label_ones, label_zeros], axis=0) - loss = fluid.layers.log_loss(fluid.layers.sigmoid(logits), label) - avg_cost = fluid.layers.reduce_sum(loss) + true_xent = fluid.layers.sigmoid_cross_entropy_with_logits(true_logits, + label_ones) + neg_xent = fluid.layers.sigmoid_cross_entropy_with_logits(neg_logits, + label_zeros) + cost = fluid.layers.elementwise_add( + fluid.layers.reduce_sum( + true_xent, dim=1), + fluid.layers.reduce_sum( + neg_xent, dim=1)) + avg_cost = fluid.layers.reduce_mean(cost) self._cost = avg_cost + global_right_cnt = fluid.layers.create_global_var( + name="global_right_cnt", + persistable=True, + dtype='float32', + shape=[1], + value=0) + global_total_cnt = fluid.layers.create_global_var( + name="global_total_cnt", + persistable=True, + dtype='float32', + shape=[1], + value=0) + global_right_cnt.stop_gradient = True + global_total_cnt.stop_gradient = True self._metrics["LOSS"] = avg_cost def optimizer(self): @@ -195,27 +240,26 @@ class Model(ModelBase): fluid.layers.equal(pred_idx, label), dtype='float32')) total_cnt = fluid.layers.reduce_sum(label_ones) - # global_right_cnt = fluid.layers.create_global_var( - # name="global_right_cnt", - # persistable=True, - # dtype='float32', - # shape=[1], - # value=0) - # global_total_cnt = fluid.layers.create_global_var( - # name="global_total_cnt", - # persistable=True, - # dtype='float32', - # shape=[1], - # value=0) - # global_right_cnt.stop_gradient = True - # global_total_cnt.stop_gradient = True - - # tmp1 = fluid.layers.elementwise_add(right_cnt, global_right_cnt) - # fluid.layers.assign(tmp1, global_right_cnt) - # tmp2 = fluid.layers.elementwise_add(total_cnt, global_total_cnt) - # fluid.layers.assign(tmp2, global_total_cnt) - - # acc = fluid.layers.elementwise_div( - # global_right_cnt, global_total_cnt, name="total_acc") - acc = fluid.layers.elementwise_div(right_cnt, total_cnt, name="acc") + global_right_cnt = fluid.layers.create_global_var( + name="global_right_cnt", + persistable=True, + dtype='float32', + shape=[1], + value=0) + global_total_cnt = fluid.layers.create_global_var( + name="global_total_cnt", + persistable=True, + dtype='float32', + shape=[1], + value=0) + global_right_cnt.stop_gradient = True + global_total_cnt.stop_gradient = True + + tmp1 = fluid.layers.elementwise_add(right_cnt, global_right_cnt) + fluid.layers.assign(tmp1, global_right_cnt) + tmp2 = fluid.layers.elementwise_add(total_cnt, global_total_cnt) + fluid.layers.assign(tmp2, global_total_cnt) + + acc = fluid.layers.elementwise_div( + global_right_cnt, global_total_cnt, name="total_acc") self._infer_results['acc'] = acc diff --git a/models/recall/word2vec/prepare_data.sh b/models/recall/word2vec/prepare_data.sh index cfd067350ce1d33112806ab72ca78222381a86f4..f7da1a10decbf944f56110016bf82137188a3456 100755 --- a/models/recall/word2vec/prepare_data.sh +++ b/models/recall/word2vec/prepare_data.sh @@ -22,16 +22,17 @@ tar xvf 1-billion-word-language-modeling-benchmark-r13output.tar mv 1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled/ raw_data/ # preprocess data -python preprocess.py --build_dict --build_dict_corpus_dir raw_data/training-monolingual.tokenized.shuffled --dict_path raw_data/test_build_dict -python preprocess.py --filter_corpus --dict_path raw_data/test_build_dict --input_corpus_dir raw_data/training-monolingual.tokenized.shuffled --output_corpus_dir raw_data/convert_text8 --min_count 5 --downsample 0.001 -mkdir thirdparty -mv raw_data/test_build_dict thirdparty/ -mv raw_data/test_build_dict_word_to_id_ thirdparty/ +python preprocess.py --build_dict --build_dict_corpus_dir raw_data/training-monolingual.tokenized.shuffled --dict_path raw_data/word_count_dict.txt +python preprocess.py --filter_corpus --dict_path raw_data/word_count_dict.txt --input_corpus_dir raw_data/training-monolingual.tokenized.shuffled --output_corpus_dir raw_data/convert_text8 --min_count 5 --downsample 0.001 +mv raw_data/word_count_dict.txt data/dict/ +mv raw_data/word_id_dict.txt data/dict/ -python preprocess.py --data_resplit --input_corpus_dir=raw_data/convert_text8 --output_corpus_dir=train_data +rm -rf data/train/* +rm -rf data/test/* +python preprocess.py --data_resplit --input_corpus_dir=raw_data/convert_text8 --output_corpus_dir=data/data # download test data wget --no-check-certificate https://paddlerec.bj.bcebos.com/word2vec/test_dir.tar tar xzvf test_dir.tar -C raw_data -mv raw_data/data/test_dir test_data/ +mv raw_data/data/test_dir data/test/ rm -rf raw_data