Closed Enjia closed 5 years ago
Same problem.
I'm using Pthon3.6 and tensorflow1.5.0.
I checked the release and commit.
This code can't work for tensorflow 1.5.0 and after release. Because the CudnnGRU's defination is changed after it.
You can choose to use tensorflow 1.4.0 or change the CudnnGRU
from tensorflow.contrib.cudnn_rnn.CudnnGRU
to tensorflow.contrib.cudnn_rnn.python.ops.CudnnGRU
That's it.
Hello, I reinstall tensorflow 1.4 and change the import, but I get: ModuleNotFoundError: No module named 'tensorflow.contrib.cudnn_rnn.python.ops.CudnnGRU' Did you have the same issue?
I had the same problem and tried Cibifangs approach. Installing tensorflow 1.4.0 resulted in the same error as: https://github.com/Arturus/kaggle-web-traffic/issues/13
It worked when I uninstalled tensorflow completely and installed tensorflow-gpu==1.4.0 instead.
Fixed by last commit
When I run this command"python trainer.py --name s32 --hparam_set=s32 --n_models=3 --name s32 --no_eval --no_forward_split --asgd_decay=0.99 --max_steps=11500 --save_from_step=10500", an error occured: /usr/local/lib/python3.6/dist-packages/h5py/init.py:36: FutureWarning: Conversion of the second argument of issubdtype from
train(**param_dict)
File "trainer.py", line 514, in train
all_models.append(create_model(scope, i, prefix=prefix, seed=seed + i))
File "trainer.py", line 471, in create_model
train_model = Model(pipe, hparams, is_train=True, graph_prefix=prefix, asgd_decay=asgd_decay, seed=seed)
File "/content/drive1/Codes/kaggle/Web_traffic_prediction/kaggle-web-traffic-master/model.py", line 371, in init
transpose_output=False)
File "/content/drive1/Codes/kaggle/Web_traffic_prediction/kaggle-web-traffic-master/model.py", line 72, in make_encoder
static_p_size = cuda_params_size(build_rnn)
File "/content/drive1/Codes/kaggle/Web_traffic_prediction/kaggle-web-traffic-master/model.py", line 46, in cuda_params_size
cuda_model = cuda_model_builder()
File "/content/drive1/Codes/kaggle/Web_traffic_prediction/kaggle-web-traffic-master/model.py", line 70, in build_rnn
dropout=hparams.encoder_dropout if is_train else 0, seed=seed)
TypeError: init() got an unexpected keyword argument 'input_size'
After that I checked the document and source code of TensorFlow to find that the params "input_size" is actually exists in the definition of CudnnGRU.Can anybody tell me why this could happen? Thanks
float
tonp.floating
is deprecated. In future, it will be treated asnp.float64 == np.dtype(float).type
. from ._conv import register_converters as _register_converters Traceback (most recent call last): File "trainer.py", line 776, in