使用 HuggingFace 和 Tensorflow 与 AutoModel 进行迁移学习不起作用
Transfer Learning using HuggingFace and Tensorflow with AutoModel does not work
我尝试使用 HuggingFace
预训练的 BERT 模型进行迁移学习。我想用它来使用 tensorflow API。我不明白为什么最后一行会产生错误
from transformers import AutoTokenizer, AutoModel
model_name = "distilbert-base-uncased"
text = "this is a test"
tokenizer = AutoTokenizer.from_pretrained(model_name)
text_tensor = tokenizer.encode(text, return_tensors="tf")
model = AutoModel.from_pretrained(model_name).to("cuda")
output = model(text_tensor) # ERROR!!, but why?
您正在混合使用 Tensorflow 和 Pytorch。
使用 TFAutoModel
而不是默认值 (Pytorch) AutoModel
from transformers import AutoTokenizer, TFAutoModel
model_name = "distilbert-base-uncased"
text = "this is a test"
tokenizer = AutoTokenizer.from_pretrained(model_name)
text_tensor = tokenizer.encode(text, return_tensors="tf")
model = TFAutoModel.from_pretrained(model_name).to("cuda")
output = model(text_tensor)
我尝试使用 HuggingFace
预训练的 BERT 模型进行迁移学习。我想用它来使用 tensorflow API。我不明白为什么最后一行会产生错误
from transformers import AutoTokenizer, AutoModel
model_name = "distilbert-base-uncased"
text = "this is a test"
tokenizer = AutoTokenizer.from_pretrained(model_name)
text_tensor = tokenizer.encode(text, return_tensors="tf")
model = AutoModel.from_pretrained(model_name).to("cuda")
output = model(text_tensor) # ERROR!!, but why?
您正在混合使用 Tensorflow 和 Pytorch。
使用 TFAutoModel
而不是默认值 (Pytorch) AutoModel
from transformers import AutoTokenizer, TFAutoModel
model_name = "distilbert-base-uncased"
text = "this is a test"
tokenizer = AutoTokenizer.from_pretrained(model_name)
text_tensor = tokenizer.encode(text, return_tensors="tf")
model = TFAutoModel.from_pretrained(model_name).to("cuda")
output = model(text_tensor)