Skip to content
#

Deep learning

Deep learning is an AI function and subset of machine learning, used for processing large amounts of complex data.

Here are 42,587 public repositories matching this topic...

transformers
NielsRogge
NielsRogge commented Jan 2, 2022

Related to #5142, AlbertTokenizer (which uses SentencePiece) doesn't decode special tokens (like [CLS], [MASK]) properly. This issue was discovered when adding the Nystromformer model (#14659), which uses this tokenizer.

To reproduce (Transformers v4.15 or below):

!pip install -q transformers sentencepiece

from transformers import AlbertTokenizer

tokenizer = AlbertTokenizer.from

Data science Python notebooks: Deep learning (TensorFlow, Theano, Caffe, Keras), scikit-learn, Kaggle, big data (Spark, Hadoop MapReduce, HDFS), matplotlib, pandas, NumPy, SciPy, Python essentials, AWS, and various command lines.

  • Updated Nov 4, 2021
  • Python
matthewdeng
matthewdeng commented Feb 14, 2022

Problem: If I don't have the necessary backend (e.g. torch) installed, a generic ModuleNotFoundError will be raised.

Reproduction:

>>> from ray.train import Trainer
>>> trainer = Trainer(backend="torch", num_workers=1)
2022-02-13 21:31:08,345	INFO services.py:1414 -- View the Ray dashboard at http://127.0.0.1:8265
2022-02-13 21:31:10,396	INFO trainer.py:199 -- Trainer
Wikipedia
Wikipedia