Final version classificator
This commit is contained in:
parent
91f262735e
commit
6939244314
@ -29,7 +29,7 @@ class CustomDataset(torch.utils.data.Dataset):
|
|||||||
return len(self.encodings["input_ids"])
|
return len(self.encodings["input_ids"])
|
||||||
|
|
||||||
data_train = list(zip(data_train_X, data_train_Y))
|
data_train = list(zip(data_train_X, data_train_Y))
|
||||||
data_train = random.sample(data_train, 5000)
|
data_train = random.sample(data_train, 180000)
|
||||||
|
|
||||||
tokenizer = BertTokenizer.from_pretrained("bert-base-uncased")
|
tokenizer = BertTokenizer.from_pretrained("bert-base-uncased")
|
||||||
train_X = tokenizer([text[0] for text in data_train], truncation=True, padding=True)
|
train_X = tokenizer([text[0] for text in data_train], truncation=True, padding=True)
|
||||||
|
Loading…
Reference in New Issue
Block a user