-
Notifications
You must be signed in to change notification settings - Fork 1.1k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
99 changed files
with
1,969 additions
and
2,691 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
149 changes: 149 additions & 0 deletions
149
deeppavlov/configs/classifiers/sentiment_twitter_bert_emb.json
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,149 @@ | ||
| { | ||
| "dataset_reader": { | ||
| "class_name": "basic_classification_reader", | ||
| "x": "Twit", | ||
| "y": "Class", | ||
| "data_path": "{DOWNLOADS_PATH}/sentiment_twitter_data" | ||
| }, | ||
| "dataset_iterator": { | ||
| "class_name": "basic_classification_iterator", | ||
| "seed": 42 | ||
| }, | ||
| "chainer": { | ||
| "in": [ | ||
| "x" | ||
| ], | ||
| "in_y": [ | ||
| "y" | ||
| ], | ||
| "pipe": [ | ||
| { | ||
| "id": "classes_vocab", | ||
| "class_name": "simple_vocab", | ||
| "fit_on": [ | ||
| "y" | ||
| ], | ||
| "save_path": "{MODEL_PATH}/classes.dict", | ||
| "load_path": "{MODEL_PATH}/classes.dict", | ||
| "in": "y", | ||
| "out": "y_ids" | ||
| }, | ||
| { | ||
| "class_name": "transformers_bert_preprocessor", | ||
| "vocab_file": "{BERT_PATH}/vocab.txt", | ||
| "do_lower_case": false, | ||
| "max_seq_length": 512, | ||
| "in": ["x"], | ||
| "out": ["tokens", "subword_tokens", "subword_tok_ids", "startofword_markers", "attention_mask"] | ||
| }, | ||
| { | ||
| "class_name": "transformers_bert_embedder", | ||
| "id": "my_embedder", | ||
| "bert_config_path": "{BERT_PATH}/bert_config.json", | ||
| "truncate": false, | ||
| "load_path": "{BERT_PATH}", | ||
| "in": ["subword_tok_ids", "startofword_markers", "attention_mask"], | ||
| "out": ["word_emb", "subword_emb", "max_emb", "mean_emb", "pooler_output"] | ||
| }, | ||
| { | ||
| "in": "y_ids", | ||
| "out": "y_onehot", | ||
| "class_name": "one_hotter", | ||
| "depth": "#classes_vocab.len", | ||
| "single_vector": true | ||
| }, | ||
| { | ||
| "in": [ | ||
| "word_emb" | ||
| ], | ||
| "in_y": [ | ||
| "y_onehot" | ||
| ], | ||
| "out": [ | ||
| "y_pred_probas" | ||
| ], | ||
| "main": true, | ||
| "class_name": "keras_classification_model", | ||
| "save_path": "{MODEL_PATH}/model", | ||
| "load_path": "{MODEL_PATH}/model", | ||
| "embedding_size": "#my_embedder.dim", | ||
| "n_classes": "#classes_vocab.len", | ||
| "kernel_sizes_cnn": [ | ||
| 3, | ||
| 5, | ||
| 7 | ||
| ], | ||
| "filters_cnn": 256, | ||
| "optimizer": "Adam", | ||
| "learning_rate": 0.01, | ||
| "learning_rate_decay": 0.1, | ||
| "loss": "binary_crossentropy", | ||
| "last_layer_activation": "softmax", | ||
| "coef_reg_cnn": 1e-3, | ||
| "coef_reg_den": 1e-2, | ||
| "dropout_rate": 0.5, | ||
| "dense_size": 100, | ||
| "model_name": "cnn_model" | ||
| }, | ||
| { | ||
| "in": "y_pred_probas", | ||
| "out": "y_pred_ids", | ||
| "class_name": "proba2labels", | ||
| "max_proba": true | ||
| }, | ||
| { | ||
| "in": "y_pred_ids", | ||
| "out": "y_pred_labels", | ||
| "ref": "classes_vocab" | ||
| } | ||
| ], | ||
| "out": [ | ||
| "y_pred_labels" | ||
| ] | ||
| }, | ||
| "train": { | ||
| "epochs": 100, | ||
| "batch_size": 64, | ||
| "metrics": [ | ||
| "accuracy", | ||
| "f1_macro", | ||
| { | ||
| "name": "roc_auc", | ||
| "inputs": ["y_onehot", "y_pred_probas"] | ||
| } | ||
| ], | ||
| "validation_patience": 5, | ||
| "val_every_n_epochs": 1, | ||
| "log_every_n_epochs": 1, | ||
| "show_examples": false, | ||
| "evaluation_targets": [ | ||
| "valid", | ||
| "test" | ||
| ], | ||
| "class_name": "nn_trainer" | ||
| }, | ||
| "metadata": { | ||
| "variables": { | ||
| "ROOT_PATH": "~/.deeppavlov", | ||
| "DOWNLOADS_PATH": "{ROOT_PATH}/downloads", | ||
| "MODELS_PATH": "{ROOT_PATH}/models", | ||
| "MODEL_PATH": "{MODELS_PATH}/classifiers/sentiment_twitter_bert_emb", | ||
| "BERT_PATH": "{DOWNLOADS_PATH}/bert_models/rubert_cased_L-12_H-768_A-12_pt" | ||
| }, | ||
| "requirements": [ | ||
| "{DEEPPAVLOV_PATH}/requirements/tf.txt", | ||
| "{DEEPPAVLOV_PATH}/requirements/transformers.txt", | ||
| "{DEEPPAVLOV_PATH}/requirements/pytorch.txt" | ||
| ], | ||
| "download": [ | ||
| { | ||
| "url": "http://files.deeppavlov.ai/datasets/sentiment_twitter_data.tar.gz", | ||
| "subdir": "{DOWNLOADS_PATH}" | ||
| }, | ||
| { | ||
| "url": "http://files.deeppavlov.ai/deeppavlov_data/bert/rubert_cased_L-12_H-768_A-12_pt.tar.gz", | ||
| "subdir": "{DOWNLOADS_PATH}/bert_models" | ||
| } | ||
| ] | ||
| } | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,43 @@ | ||
| { | ||
| "chainer": { | ||
| "in": ["texts"], | ||
| "pipe": [ | ||
| { | ||
| "class_name": "transformers_bert_preprocessor", | ||
| "vocab_file": "{BERT_PATH}/vocab.txt", | ||
| "do_lower_case": false, | ||
| "max_seq_length": 512, | ||
| "in": ["texts"], | ||
| "out": ["tokens", "subword_tokens", "subword_tok_ids", "startofword_markers", "attention_mask"] | ||
| }, | ||
| { | ||
| "class_name": "transformers_bert_embedder", | ||
| "bert_config_path": "{BERT_PATH}/bert_config.json", | ||
| "load_path": "{BERT_PATH}", | ||
| "truncate": true, | ||
| "in": ["subword_tok_ids", "startofword_markers", "attention_mask"], | ||
| "out": ["word_emb", "subword_emb", "max_emb", "mean_emb", "pooler_output"] | ||
| } | ||
| ], | ||
| "out": ["tokens", "word_emb", "subword_tokens", "subword_emb", "max_emb", "mean_emb", "pooler_output"] | ||
| }, | ||
| "train": {}, | ||
| "metadata": { | ||
| "variables": { | ||
| "ROOT_PATH": "~/.deeppavlov", | ||
| "DOWNLOADS_PATH": "{ROOT_PATH}/downloads", | ||
| "BERT_PATH": "{DOWNLOADS_PATH}/bert_models/multi_cased_L-12_H-768_A-12_pt" | ||
| }, | ||
| "requirements": [ | ||
| "{DEEPPAVLOV_PATH}/requirements/transformers.txt", | ||
| "{DEEPPAVLOV_PATH}/requirements/pytorch.txt" | ||
| ], | ||
| "labels": {}, | ||
| "download": [ | ||
| { | ||
| "url": "http://files.deeppavlov.ai/deeppavlov_data/bert/multi_cased_L-12_H-768_A-12_pt.tar.gz", | ||
| "subdir": "{DOWNLOADS_PATH}/bert_models" | ||
| } | ||
| ] | ||
| } | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,43 @@ | ||
| { | ||
| "chainer": { | ||
| "in": ["texts"], | ||
| "pipe": [ | ||
| { | ||
| "class_name": "transformers_bert_preprocessor", | ||
| "vocab_file": "{BERT_PATH}/vocab.txt", | ||
| "do_lower_case": false, | ||
| "max_seq_length": 512, | ||
| "in": ["texts"], | ||
| "out": ["tokens", "subword_tokens", "subword_tok_ids", "startofword_markers", "attention_mask"] | ||
| }, | ||
| { | ||
| "class_name": "transformers_bert_embedder", | ||
| "bert_config_path": "{BERT_PATH}/bert_config.json", | ||
| "load_path": "{BERT_PATH}", | ||
| "truncate": false, | ||
| "in": ["subword_tok_ids", "startofword_markers", "attention_mask"], | ||
| "out": ["word_emb", "subword_emb", "max_emb", "mean_emb", "pooler_output"] | ||
| } | ||
| ], | ||
| "out": ["max_emb", "mean_emb", "pooler_output"] | ||
| }, | ||
| "train": {}, | ||
| "metadata": { | ||
| "variables": { | ||
| "ROOT_PATH": "~/.deeppavlov", | ||
| "DOWNLOADS_PATH": "{ROOT_PATH}/downloads", | ||
| "BERT_PATH": "{DOWNLOADS_PATH}/bert_models/sentence_multi_cased_L-12_H-768_A-12_pt" | ||
| }, | ||
| "requirements": [ | ||
| "{DEEPPAVLOV_PATH}/requirements/transformers.txt", | ||
| "{DEEPPAVLOV_PATH}/requirements/pytorch.txt" | ||
| ], | ||
| "labels": {}, | ||
| "download": [ | ||
| { | ||
| "url": "http://files.deeppavlov.ai/deeppavlov_data/bert/sentence_multi_cased_L-12_H-768_A-12_pt.tar.gz", | ||
| "subdir": "{DOWNLOADS_PATH}/bert_models" | ||
| } | ||
| ] | ||
| } | ||
| } |
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.