AttributeError: 'Dense' object has no attribute 'b'

[yanshengjia]

When I run "python train_nea.py -tr data/fold_0/train.tsv -tu data/fold_0/dev.tsv -ts data/fold_0/test.tsv -p 1 -o output"

I got an error like this:

/Users/yanshengjia/Desktop/aes/nea/nea/models.py:63: UserWarning: Update your LSTM call to the Keras 2 API: LSTM(300, return_sequences=True, dropout=0.5, recurrent_dropout=0.1)
model.add(RNN(args.rnn_dim, return_sequences=True, dropout_W=dropout_W, dropout_U=dropout_U))
/Users/yanshengjia/anaconda/lib/python2.7/site-packages/keras/engine/topology.py:621: UserWarning: Class nea.my_layers.MeanOverTime defines get_output_shape_for but does not override compute_output_shape. If this is a Keras 1 layer, please implement compute_output_shape to support Keras 2.
output_shape = self.compute_output_shape(input_shape)
Traceback (most recent call last):
File "train_nea.py", line 160, in
model = create_model(args, train_y.mean(axis=0), overal_maxlen, vocab)
File "/Users/yanshengjia/Desktop/aes/nea/nea/models.py", line 73, in create_model
model.layers[-1].b.set_value(bias_value)
AttributeError: 'Dense' object has no attribute 'b'

[izk8]

I got that when using Keras 2 something.

Downgrading to Keras to 1.1.0. is very important to getting this code to work in its current state.

I did it through creating a vitualenv so it would have the correct dependencies.

[yanshengjia]

This error occurred because the outdated Keras calls in nea.

I have updated them and make nea compatible with Keras 2.0.8.

Please refer to this page.

[DamonCC]

I got that when using Keras 2 something.

Downgrading to Keras to 1.1.0. is very important to getting this code to work in its current state.

I did it through creating a vitualenv so it would have the correct dependencies.

Can you tell me all your environment dependent versions?