-
Hello, I would like to know where should I put the wjs0-mix dataset in order to generate the RIR dataset？
-
First, Thanks for the great work.
Does nnabla C++ support BLSTM model inference now? if so, is there any docs or example?
-
The BLSTM layer is defined in Keras like:
```
x2 = Bidirectional(LSTM(128,return_sequences=True),name='blstm')(x1)
```
which has 128 units. The input shape of BLSTM is [32,32,512] and the output …
-
I tried to solve some error related to an unset Batch Dimension, but it is unclear what should actually be set. Currently neither `.dimension` or `.dyn_size_ext` is set.
So for a single update step…
-
After every epoch I get:
```python3
reinit because network description differs. Diff: item 'encoder' dict differs:
item 'out_shape' differ. self: {Dim{'data_time'[B(-1)]}, Dim{B}, Dim{F'2*(BLSTM-…
-
**System information**
- OS Platform and Distribution (e.g., Linux Ubuntu 16.04): MacOs M1 (12.0 Beta Monterey)
- TensorFlow version and how it was installed (source or binary): 2.5.0 (pip)
- Tenso…
-
微博内容精选
-
I train a model using CNN and BLSTM with keras 2.0.8 using tensorflow as backend. The "AttributeError: The layer has never been called and thus has no defined input shape" occurred when converting to …
-
Hi,
How I can tune the number of epochs and batch size?
The provided examples always assume fixed values for these two hyperparameters.
-
**Describe the bug**
A clear and concise description of what the bug is.
**Basic environments:**
- OS information: [Linux 5.15.0-52-generic #58~20.04.1-Ubuntu SMP Thu Oct 13 13:09:46 UTC 2022 x8…