python - 属性错误: module 'tensorflow_core.python.keras.api._v2.keras.activations' has no attribute 'swish'

Question

我正在使用 Azure ML studio 使用 SQuAD 数据集训练问答 ALBERT 模型。我收到以下错误。这是我执行的代码。

# Clone transformers github repo
!git clone https://github.com/huggingface/transformers \
&& cd transformers \
&& git checkout a3085020ed0d81d4903c50967687192e3101e770 

# Install libraries
# !pip install ./transformers
!pip install transformers
!pip install tensorboardX

# Get data
! mkdir dataset \
&& cd dataset \
&& wget https://rajpurkar.github.io/SQuAD-explorer/dataset/train-v2.0.json \
&& wget https://rajpurkar.github.io/SQuAD-explorer/dataset/dev-v2.0.json

# Train model
!export SQUAD_DIR=/content/dataset \
&& python transformers/examples/run_squad.py \
    --model_type albert \
    --model_name_or_path albert-base-v2 \
    --do_train \
    --do_eval \
    --do_lower_case \
    --train_file $SQUAD_DIR/train-v2.0.json \
    --predict_file $SQUAD_DIR/dev-v2.0.json \
    --per_gpu_train_batch_size 12 \
    --learning_rate 3e-5 \
    --num_train_epochs 1.0 \
    --max_seq_length 384 \
    --doc_stride 128 \
    --output_dir /content/model_output \
    --save_steps 1000 \
    --threads 4 \
    --version_2_with_negative 

我使用的是 NVIDIA Tesla K80 GPU。当我执行上面的单元格来训练模型时，出现以下错误:

2020-10-31 01:31:45.732913: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'libnvinfer.so.6'; dlerror: libnvinfer.so.6: cannot open shared object file: No such file or directory
2020-10-31 01:31:45.733023: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'libnvinfer_plugin.so.6'; dlerror: libnvinfer_plugin.so.6: cannot open shared object file: No such file or directory
2020-10-31 01:31:45.733043: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:30] Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.
Traceback (most recent call last):
    File "transformers/examples/run_squad.py", line 32, in <module>
    from transformers import (
    File "/anaconda/envs/azureml_py36/lib/python3.6/site-packages/transformers/__init__.py", line 135, in <module>
    from .pipelines import (
    File "/anaconda/envs/azureml_py36/lib/python3.6/site-packages/transformers/pipelines.py", line 47, in <module>
    from .modeling_tf_auto import (
    File "/anaconda/envs/azureml_py36/lib/python3.6/site-packages/transformers/modeling_tf_auto.py", line 45, in <module>
    from .modeling_tf_albert import (
    File "/anaconda/envs/azureml_py36/lib/python3.6/site-packages/transformers/modeling_tf_albert.py", line 24, in <module>
    from .activations_tf import get_tf_activation
    File "/anaconda/envs/azureml_py36/lib/python3.6/site-packages/transformers/activations_tf.py", line 53, in <module>
    "swish": tf.keras.activations.swish,
AttributeError: module 'tensorflow_core.python.keras.api._v2.keras.activations' has no attribute 'swish'

Answer 1

已解决

需要添加:

!pip3 install --upgrade tensorflow-gpu # for Python 3.n and GPU