Spaces:
Runtime error
Runtime error
Commit
·
5f849fb
1
Parent(s):
a0a875f
Update app.py
Browse files
app.py
CHANGED
|
@@ -10,6 +10,14 @@ from numpy.linalg import norm
|
|
| 10 |
# compute dot product of inputs
|
| 11 |
# summary function - test for single gradio function interfrace
|
| 12 |
def gr_cosine_similarity(sentence1, sentence2):
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
# Create class for data preparation
|
| 14 |
class SimpleDataset:
|
| 15 |
def __init__(self, tokenized_texts):
|
|
@@ -21,19 +29,10 @@ def gr_cosine_similarity(sentence1, sentence2):
|
|
| 21 |
def __getitem__(self, idx):
|
| 22 |
return {k: v[idx] for k, v in self.tokenized_texts.items()}
|
| 23 |
|
| 24 |
-
|
| 25 |
-
model_name = "j-hartmann/emotion-english-distilroberta-base"
|
| 26 |
-
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
| 27 |
-
model = AutoModelForSequenceClassification.from_pretrained(model_name)
|
| 28 |
-
trainer = Trainer(model=model)
|
| 29 |
-
|
| 30 |
-
|
| 31 |
# sentences in list
|
| 32 |
lines_s = [sentence1, sentence2]
|
| 33 |
-
|
| 34 |
-
print(sentence1, sentence2)
|
| 35 |
-
print(lines_s)
|
| 36 |
-
|
| 37 |
# Tokenize texts and create prediction data set
|
| 38 |
tokenized_texts = tokenizer(lines_s, truncation=True, padding=True)
|
| 39 |
pred_dataset = SimpleDataset(tokenized_texts)
|
|
@@ -49,7 +48,7 @@ def gr_cosine_similarity(sentence1, sentence2):
|
|
| 49 |
temp = (np.exp(predictions[0])/np.exp(predictions[0]).sum(-1, keepdims=True)).tolist()
|
| 50 |
|
| 51 |
|
| 52 |
-
|
| 53 |
# container
|
| 54 |
anger = []
|
| 55 |
disgust = []
|
|
@@ -59,7 +58,6 @@ def gr_cosine_similarity(sentence1, sentence2):
|
|
| 59 |
sadness = []
|
| 60 |
surprise = []
|
| 61 |
|
| 62 |
-
print(temp)
|
| 63 |
# extract scores (as many entries as exist in pred_texts)
|
| 64 |
for i in range(len(lines_s)):
|
| 65 |
anger.append(temp[i][0])
|
|
@@ -74,7 +72,7 @@ def gr_cosine_similarity(sentence1, sentence2):
|
|
| 74 |
# each include all values for both predictions
|
| 75 |
v1 = temp[0]
|
| 76 |
v2 = temp[1]
|
| 77 |
-
|
| 78 |
# compute dot product of all
|
| 79 |
dot_product = dot(v1, v2)
|
| 80 |
|
|
|
|
| 10 |
# compute dot product of inputs
|
| 11 |
# summary function - test for single gradio function interfrace
|
| 12 |
def gr_cosine_similarity(sentence1, sentence2):
|
| 13 |
+
|
| 14 |
+
# load tokenizer and model, create trainer
|
| 15 |
+
model_name = "j-hartmann/emotion-english-distilroberta-base"
|
| 16 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
| 17 |
+
model = AutoModelForSequenceClassification.from_pretrained(model_name)
|
| 18 |
+
trainer = Trainer(model=model)
|
| 19 |
+
|
| 20 |
+
|
| 21 |
# Create class for data preparation
|
| 22 |
class SimpleDataset:
|
| 23 |
def __init__(self, tokenized_texts):
|
|
|
|
| 29 |
def __getitem__(self, idx):
|
| 30 |
return {k: v[idx] for k, v in self.tokenized_texts.items()}
|
| 31 |
|
| 32 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
# sentences in list
|
| 34 |
lines_s = [sentence1, sentence2]
|
| 35 |
+
|
|
|
|
|
|
|
|
|
|
| 36 |
# Tokenize texts and create prediction data set
|
| 37 |
tokenized_texts = tokenizer(lines_s, truncation=True, padding=True)
|
| 38 |
pred_dataset = SimpleDataset(tokenized_texts)
|
|
|
|
| 48 |
temp = (np.exp(predictions[0])/np.exp(predictions[0]).sum(-1, keepdims=True)).tolist()
|
| 49 |
|
| 50 |
|
| 51 |
+
# work in progress
|
| 52 |
# container
|
| 53 |
anger = []
|
| 54 |
disgust = []
|
|
|
|
| 58 |
sadness = []
|
| 59 |
surprise = []
|
| 60 |
|
|
|
|
| 61 |
# extract scores (as many entries as exist in pred_texts)
|
| 62 |
for i in range(len(lines_s)):
|
| 63 |
anger.append(temp[i][0])
|
|
|
|
| 72 |
# each include all values for both predictions
|
| 73 |
v1 = temp[0]
|
| 74 |
v2 = temp[1]
|
| 75 |
+
|
| 76 |
# compute dot product of all
|
| 77 |
dot_product = dot(v1, v2)
|
| 78 |
|