Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

train.sh results in an error #30

Open
GopinathCool opened this issue Apr 21, 2021 · 0 comments
Open

train.sh results in an error #30

GopinathCool opened this issue Apr 21, 2021 · 0 comments

Comments

@GopinathCool
Copy link

I tried to run train.sh, but after running I am receiving the below error,

{'stride_conv1': [2, 2], 'bn_model': ['./models/bn_params.npz'], 'GrowthRate': [24], 'input_channels': [1], 'learning-rate': [1e-08], 'clip-c': [100.0], 'channel_conv1': [48], 'kernel_conv1': [7, 7], 'DenseBlock': [16, 16, 16], 'dim_coverage': [512], 'maxImagesize': [500000], 'Bottleneck': [True], 'dim_dec': [256], 'use-dropout': [True], 'kernel_coverage': [11, 11], 'optimizer': ['adadelta'], 'decay-c': [0.0001], 'Transition': [0.5], 'dim_target': [111], 'dim_word': [256], 'reload': [False], 'dim_attention': [512], 'maxlen': [200], 'model': ['./models/attention_maxlen[200]_dimWord256_dim256.npz']}
total words/phones 111
Loading data
total 1226 batch data loaded
sentence 505_em_51 length bigger than 200 ignore
total 138 batch data loaded
Building model
Traceback (most recent call last):
File "train_nmt.py", line 97, in
'reload': [False]})
File "train_nmt.py", line 49, in main
use_dropout=params['use-dropout'][0])
File "/content/WAP/DenseNet/nmt.py", line 1165, in train
build_model(tparams, bn_tparams, model_options)
File "/content/WAP/DenseNet/nmt.py", line 641, in build_model
dnn_batch_normalization_train(oup, bn_gamma, bn_beta, mode='spatial', running_mean=bn_mean, running_var=bn_var)
File "/usr/local/lib/python2.7/dist-packages/theano/gpuarray/dnn.py", line 2809, in dnn_batch_normalization_train
gpu_contiguous(inputs), gpu_contiguous(gamma),
File "/usr/local/lib/python2.7/dist-packages/theano/gof/op.py", line 615, in call
node = self.make_node(*inputs, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/theano/gpuarray/basic_ops.py", line 1078, in make_node
context_name=infer_context_name(input))
File "/usr/local/lib/python2.7/dist-packages/theano/gpuarray/basic_ops.py", line 127, in infer_context_name
raise ValueError("Could not infer context from inputs")
ValueError: Could not infer context from inputs

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant