小编Mar*_*ach的帖子

AttributeError:模块“tensorflow_core.python.keras.api._v2.keras.activations”没有属性“swish”

我正在使用 Azure ML Studio 来训练一个带有 SQuAD 数据集的问答 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 …
Run Code Online (Sandbox Code Playgroud)

python azure azure-machine-learning-studio jupyter-notebook azure-machine-learning-service

3
推荐指数
1
解决办法
7451
查看次数