如何解决Universal Sentence Encoder,输入必须是向量,得到形状:[]
我正在使用 USE 进行英国脱欧推文的立场检测项目。对于我的代码,我正在尝试应用此笔记本:https://www.kaggle.com/kshitijmohan/sentiment-analysis-universal-sentence-encoder-91
但我收到此错误:
input must be a vector,got shape: []
(t_stance 是立场,0 = 保持,1 = 离开,2 = 中立)
RANDOM_SEED = 42
np.random.seed(RANDOM_SEED)
tf.random.set_seed(RANDOM_SEED)
train = pd.read_csv(base_dir + "k500_train.csv")
module_url = "https://tfhub.dev/google/universal-sentence-encoder/4"
use = hub.load(module_url)
from sklearn.preprocessing import OneHotEncoder
type_one_hot = OneHotEncoder(sparse=False).fit_transform(
train.t_stance.to_numpy().reshape(-1,1)
)
train_reviews,test_reviews,y_train,y_test =\
train_test_split(
train.text,type_one_hot,test_size=.4,random_state=42
)
X_train = []
for r in tqdm(train_reviews):
emb = use(r)
review_emb = tf.reshape(emb,[-1]).numpy()
X_train.append(review_emb)
X_train = np.array(X_train)
0%| | 0/210000 [00:01<?,?it/s]
InvalidArgumentError: input must be a vector,got shape: []
[[{{node StatefulPartitionedCall/StatefulPartitionedCall/text_preprocessor/tokenize/StringSplit/StringSplit}}]] [Op:__inference_restored_function_body_10218]
Function call stack:
restored_function_body
版权声明:本文内容由互联网用户自发贡献,该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容, 请发送邮件至 dio@foxmail.com 举报,一经查实,本站将立刻删除。