Skip to content
This repository has been archived by the owner on Oct 18, 2020. It is now read-only.

ValueError #22

Open
pku-H2R opened this issue Mar 11, 2019 · 2 comments
Open

ValueError #22

pku-H2R opened this issue Mar 11, 2019 · 2 comments

Comments

@pku-H2R
Copy link

pku-H2R commented Mar 11, 2019

File "D:\Anaconda\lib\site-packages\ann_visualizer\visualize.py", line 42, in ann_viz
input_layer = int(str(layer.input_shape).split(",")[1][1:-1]);
ValueError: invalid literal for int() with base 10: ''

@pikaliov
Copy link

pikaliov commented Apr 18, 2019

I have same error (using Keras API)

input_ = Input(batch_shape=(None, 1, dim_in), name='main_input')
out = Bidirectional(CuDNNGRU(256, return_sequences=True), name='BLSTM-256')(input_)
out = Bidirectional(CuDNNGRU(128, return_sequences=True), name='BLSTM-128')(out)
out = Bidirectional(CuDNNGRU(64, return_sequences=True), name='BLSTM-64')(out)
out = Bidirectional(CuDNNGRU(1, return_sequences=True), name='BLSTM-1')(out)
out = TimeDistributed(Dense(dim_out, activation='linear',), name='main_out')(out)
m = Model(inputs=[input_], outputs=[out])

X_train = [1900, 1, 6]
Y_train = [1900, 1, 4]

@pikaliov
Copy link

m_stack_blstm_mask

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

No branches or pull requests

2 participants