Update README.md
Browse files
README.md
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
---
|
2 |
-
|
3 |
license: mit
|
4 |
-
language:
|
|
|
5 |
tags:
|
6 |
- russian
|
7 |
- classification
|
@@ -10,15 +10,16 @@ tags:
|
|
10 |
- emotion-recognition
|
11 |
- multiclass
|
12 |
widget:
|
13 |
-
- text:
|
14 |
-
- text:
|
15 |
-
- text:
|
16 |
-
- text:
|
17 |
-
- text:
|
18 |
-
- text:
|
|
|
|
|
19 |
datasets:
|
20 |
-
- Djacon/
|
21 |
-
|
22 |
---
|
23 |
|
24 |
# First - you should prepare few functions to talk to model
|
@@ -27,7 +28,7 @@ datasets:
|
|
27 |
import torch
|
28 |
from transformers import BertForSequenceClassification, AutoTokenizer
|
29 |
|
30 |
-
|
31 |
tokenizer = AutoTokenizer.from_pretrained('Djacon/rubert-tiny2-russian-emotion-detection')
|
32 |
model = BertForSequenceClassification.from_pretrained('Djacon/rubert-tiny2-russian-emotion-detection')
|
33 |
|
@@ -36,27 +37,28 @@ model = BertForSequenceClassification.from_pretrained('Djacon/rubert-tiny2-russi
|
|
36 |
def predict_emotion(text: str) -> str:
|
37 |
inputs = tokenizer(text, truncation=True, return_tensors='pt')
|
38 |
inputs = inputs.to(model.device)
|
39 |
-
|
40 |
outputs = model(**inputs)
|
41 |
-
|
42 |
-
pred = torch.nn.functional.
|
43 |
pred = pred.argmax(dim=1)
|
|
|
|
|
44 |
|
45 |
-
return LABELS[pred[0]]
|
46 |
|
47 |
# Probabilistic prediction of emotion in a text
|
48 |
@torch.no_grad()
|
49 |
-
def predict_emotions(text: str) ->
|
50 |
inputs = tokenizer(text, truncation=True, return_tensors='pt')
|
51 |
inputs = inputs.to(model.device)
|
52 |
|
53 |
outputs = model(**inputs)
|
54 |
|
55 |
-
pred = torch.nn.functional.
|
56 |
|
57 |
emotions_list = {}
|
58 |
for i in range(len(pred[0].tolist())):
|
59 |
-
emotions_list[
|
60 |
return emotions_list
|
61 |
```
|
62 |
|
@@ -68,8 +70,8 @@ not_simple_prediction = predict_emotions("Какой же сегодня пре
|
|
68 |
|
69 |
print(simple_prediction)
|
70 |
print(not_simple_prediction)
|
71 |
-
#
|
72 |
-
# {'
|
73 |
```
|
74 |
|
75 |
# Citations
|
|
|
1 |
---
|
|
|
2 |
license: mit
|
3 |
+
language:
|
4 |
+
- ru
|
5 |
tags:
|
6 |
- russian
|
7 |
- classification
|
|
|
10 |
- emotion-recognition
|
11 |
- multiclass
|
12 |
widget:
|
13 |
+
- text: Как дела?
|
14 |
+
- text: Дурак твой дед
|
15 |
+
- text: Только попробуй!!!
|
16 |
+
- text: Не хочу в школу(
|
17 |
+
- text: Сейчас ровно час дня
|
18 |
+
- text: >-
|
19 |
+
А ты уверен, что эти полоски снизу не врут? Точно уверен? Вот прям 100
|
20 |
+
процентов?
|
21 |
datasets:
|
22 |
+
- Djacon/ru_go_emotions
|
|
|
23 |
---
|
24 |
|
25 |
# First - you should prepare few functions to talk to model
|
|
|
28 |
import torch
|
29 |
from transformers import BertForSequenceClassification, AutoTokenizer
|
30 |
|
31 |
+
LABELS_RU = ['нейтрально', 'радость', 'грусть', 'гнев', 'интерес', 'удивление', 'отвращение', 'страх', 'вина', 'стыд']
|
32 |
tokenizer = AutoTokenizer.from_pretrained('Djacon/rubert-tiny2-russian-emotion-detection')
|
33 |
model = BertForSequenceClassification.from_pretrained('Djacon/rubert-tiny2-russian-emotion-detection')
|
34 |
|
|
|
37 |
def predict_emotion(text: str) -> str:
|
38 |
inputs = tokenizer(text, truncation=True, return_tensors='pt')
|
39 |
inputs = inputs.to(model.device)
|
40 |
+
|
41 |
outputs = model(**inputs)
|
42 |
+
|
43 |
+
pred = torch.nn.functional.sigmoid(outputs.logits)
|
44 |
pred = pred.argmax(dim=1)
|
45 |
+
|
46 |
+
return LABELS_RU[pred[0]]
|
47 |
|
|
|
48 |
|
49 |
# Probabilistic prediction of emotion in a text
|
50 |
@torch.no_grad()
|
51 |
+
def predict_emotions(text: str) -> dict:
|
52 |
inputs = tokenizer(text, truncation=True, return_tensors='pt')
|
53 |
inputs = inputs.to(model.device)
|
54 |
|
55 |
outputs = model(**inputs)
|
56 |
|
57 |
+
pred = torch.nn.functional.sigmoid(outputs.logits)
|
58 |
|
59 |
emotions_list = {}
|
60 |
for i in range(len(pred[0].tolist())):
|
61 |
+
emotions_list[LABELS_RU[i]] = round(pred[0].tolist()[i], 4)
|
62 |
return emotions_list
|
63 |
```
|
64 |
|
|
|
70 |
|
71 |
print(simple_prediction)
|
72 |
print(not_simple_prediction)
|
73 |
+
# радость
|
74 |
+
# {'нейтрально': 0.1985, 'радость': 0.7419, 'грусть': 0.0261, 'гнев': 0.0295, 'интерес': 0.1983, 'удивление': 0.4305, 'отвращение': 0.0082, 'страх': 0.008, 'вина': 0.0046, 'стыд': 0.0097}
|
75 |
```
|
76 |
|
77 |
# Citations
|