Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

New classification models #1651

Closed
wants to merge 23 commits into from
Closed

New classification models #1651

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
23 commits
Select commit Hold shift + click to select a range
1a59449
Release 1.0.0
IgnatovFedor Nov 8, 2022
49e74be
Release 1.0.1
IgnatovFedor Nov 22, 2022
a1e9477
Release 1.0.2
IgnatovFedor Jan 10, 2023
8d8bdaf
Release 1.1.0
IgnatovFedor Feb 17, 2023
0448c73
Release 1.1.1
IgnatovFedor Mar 14, 2023
d39944b
Release 1.2.0
IgnatovFedor Jun 6, 2023
71bf956
Added new config for intents classification model
Kolpnick Jun 26, 2023
1cfefbb
Added new config for emotions classifier model
Kolpnick Jun 26, 2023
fcc8c7f
Added new config for sentiments classification model
Kolpnick Jun 26, 2023
8ef89ca
Added new config for topics classification model
Kolpnick Jun 26, 2023
32ba7e0
Added new config for insults classification model
Kolpnick Jun 30, 2023
101cdb8
Added the ability to run on multiple GPUs
Kolpnick Jul 4, 2023
b375877
Deleted redundant code
Kolpnick Jul 4, 2023
81e3299
Merge branch 'deeppavlov:master' into feat/intents_classification
Kolpnick Jul 4, 2023
992003c
Added new config for NER model
Kolpnick Jul 6, 2023
1f02857
Updated download path
Kolpnick Jul 11, 2023
fd42b2e
Added tests for new models
Kolpnick Jul 11, 2023
8379016
Merge branch 'dev' into feat/intents_classification
Kolpnick Jul 12, 2023
f1261f5
Fixed bug when using GPU
Kolpnick Jul 12, 2023
42190ca
Fixed tests for new models
Kolpnick Jul 12, 2023
2e6cfe8
Fixed bug with missing positional argument
Kolpnick Jul 13, 2023
a55a03e
Added input concatenation for ner models
Kolpnick Jul 24, 2023
81cccf3
Updated NER model
Kolpnick Jul 24, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
105 changes: 105 additions & 0 deletions deeppavlov/configs/classifiers/emotions_xlm_roberta_base.json
View file
Open in desktop
@@ -0,0 +1,105 @@
{
"dataset_reader": {
"class_name": "huggingface_dataset_reader",
"path": "cedr",
"name": "main",
"train": "train",
"test": "test"
},
"dataset_iterator": {
"class_name": "huggingface_dataset_iterator",
"features": "text",
"label": "labels",
"seed": 42
},
"chainer": {
"in": ["x"],
"in_y": ["y"],
"pipe": [
{
"class_name": "torch_transformers_preprocessor",
"vocab_file": "{BASE_MODEL}",
"do_lower_case": false,
"max_seq_length": 128,
"in": ["x"],
"out": ["bert_features"]
},
{
"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"]
},
{
"in": ["y_ids"],
"out": ["y_onehot"],
"class_name": "one_hotter",
"depth": "#classes_vocab.len",
"single_vector": true
},
{
"class_name": "torch_transformers_classifier",
"n_classes": "#classes_vocab.len",
"return_probas": true,
"pretrained_bert": "{BASE_MODEL}",
"save_path": "{MODEL_PATH}/model",
"load_path": "{MODEL_PATH}/model",
"optimizer": "AdamW",
"optimizer_parameters": {
"lr": 1e-05
},
"learning_rate_drop_patience": 3,
"learning_rate_drop_div": 2.0,
"in": ["bert_features"],
"in_y": ["y_ids"],
"out": ["y_pred_probas"]
},
{
"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": {
"batch_size": 64,
"metrics": [
"accuracy",
"f1_weighted",
"f1_macro"
],
"validation_patience": 10,
"val_every_n_epochs": 1,
"log_every_n_epochs": 1,
"show_examples": false,
"evaluation_targets": ["train", "test"],
"class_name": "torch_trainer",
"tensorboard_log_dir": "{MODEL_PATH}/",
"pytest_max_batches": 2
},
"metadata": {
"variables": {
"BASE_MODEL": "xlm-roberta-base",
"ROOT_PATH": "~/.deeppavlov",
"DOWNLOADS_PATH": "{ROOT_PATH}/downloads",
"MODELS_PATH": "{ROOT_PATH}/models",
"MODEL_PATH": "{MODELS_PATH}/emotions_classifier/{BASE_MODEL}"
},
"download": [
{
"url": "http://files.deeppavlov.ai/v1/classifiers/emotions/emotions_xlm_roberta_base.tar.gz",
"subdir": "{MODEL_PATH}"
}
]
}
}
106 changes: 106 additions & 0 deletions deeppavlov/configs/classifiers/insults_xlm_roberta_base.json
View file
Open in desktop
@@ -0,0 +1,106 @@
{
"dataset_reader": {
"class_name": "basic_classification_reader",
"x": "Comment",
"y": "Class",
"data_path": "{DOWNLOADS_PATH}/insults_data"
},
"dataset_iterator": {
"class_name": "basic_classification_iterator",
"seed": 42
},
"chainer": {
"in": ["x"],
"in_y": ["y"],
"pipe": [
{
"class_name": "torch_transformers_preprocessor",
"vocab_file": "{BASE_MODEL}",
"do_lower_case": false,
"max_seq_length": 128,
"in": ["x"],
"out": ["bert_features"]
},
{
"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"]
},
{
"in": ["y_ids"],
"out": ["y_onehot"],
"class_name": "one_hotter",
"depth": "#classes_vocab.len",
"single_vector": true
},
{
"class_name": "torch_transformers_classifier",
"n_classes": "#classes_vocab.len",
"return_probas": true,
"pretrained_bert": "{BASE_MODEL}",
"save_path": "{MODEL_PATH}/model",
"load_path": "{MODEL_PATH}/model",
"optimizer": "AdamW",
"optimizer_parameters": {
"lr": 1e-05
},
"learning_rate_drop_patience": 3,
"learning_rate_drop_div": 2.0,
"in": ["bert_features"],
"in_y": ["y_ids"],
"out": ["y_pred_probas"]
},
{
"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": {
"batch_size": 256,
"metrics": [
"accuracy",
"f1_weighted",
"f1_macro"
],
"validation_patience": 10,
"val_every_n_epochs": 1,
"log_every_n_epochs": 1,
"show_examples": false,
"evaluation_targets": ["train", "valid"],
"class_name": "torch_trainer",
"tensorboard_log_dir": "{MODEL_PATH}/",
"pytest_max_batches": 2
},
"metadata": {
"variables": {
"BASE_MODEL": "xlm-roberta-base",
"ROOT_PATH": "~/.deeppavlov",
"DOWNLOADS_PATH": "{ROOT_PATH}/downloads",
"MODELS_PATH": "{ROOT_PATH}/models",
"MODEL_PATH": "{MODELS_PATH}/insults_classifier/{BASE_MODEL}"
},
"download": [
{
"url": "http://files.deeppavlov.ai/datasets/insults_data.tar.gz",
"subdir": "{DOWNLOADS_PATH}"
},
{
"url": "http://files.deeppavlov.ai/v1/classifiers/insults/insults_xlm_roberta_base.tar.gz",
"subdir": "{MODEL_PATH}"
}
]
}
}
105 changes: 105 additions & 0 deletions deeppavlov/configs/classifiers/intents_distilbert_base_multi.json
View file
Open in desktop
@@ -0,0 +1,105 @@
{
"dataset_reader": {
"class_name": "huggingface_dataset_reader",
"path": "AmazonScience/massive",
"name": "all",
"train": "train",
"valid": "validation",
"test": "test"
},
"dataset_iterator": {
"class_name": "huggingface_dataset_iterator",
"features": "utt",
"label": "intent",
"seed": 42
},
"chainer": {
"in": ["x"],
"in_y": ["y"],
"pipe": [
{
"class_name": "torch_transformers_preprocessor",
"vocab_file": "{BASE_MODEL}",
"do_lower_case": false,
"max_seq_length": 128,
"in": ["x"],
"out": ["bert_features"]
},
{
"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"]
},
{
"in": ["y_ids"],
"out": ["y_onehot"],
"class_name": "one_hotter",
"depth": "#classes_vocab.len",
"single_vector": true
},
{
"class_name": "torch_transformers_classifier",
"n_classes": "#classes_vocab.len",
"return_probas": true,
"pretrained_bert": "{BASE_MODEL}",
"save_path": "{MODEL_PATH}/model",
"load_path": "{MODEL_PATH}/model",
"optimizer": "AdamW",
"optimizer_parameters": {
"lr": 2e-05
},
"learning_rate_drop_patience": 3,
"learning_rate_drop_div": 2.0,
"in": ["bert_features"],
"in_y": ["y_ids"],
"out": ["y_pred_probas"]
},
{
"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": {
"batch_size": 128,
"metrics": [
"accuracy",
"f1_weighted"
],
"validation_patience": 10,
"val_every_n_epochs": 1,
"log_every_n_epochs": 1,
"show_examples": false,
"evaluation_targets": ["train", "valid"],
"class_name": "torch_trainer",
"tensorboard_log_dir": "{MODEL_PATH}/",
"pytest_max_batches": 2
},
"metadata": {
"variables": {
"BASE_MODEL": "distilbert-base-multilingual-cased",
"ROOT_PATH": "~/.deeppavlov",
"DOWNLOADS_PATH": "{ROOT_PATH}/downloads",
"MODELS_PATH": "{ROOT_PATH}/models",
"MODEL_PATH": "{MODELS_PATH}/intents_classification/{BASE_MODEL}"
},
"download": [
{
"url": "http://files.deeppavlov.ai/v1/classifiers/intents/intents_classification_distilbert_multi.tar.gz",
"subdir": "{MODEL_PATH}"
}
]
}
}