-
Should there not be an activation function after the first *3, Temp Conv, 64* layer? The paper does not specify but I assumed every convolutional layer should be followed by batch normalization + relu…
-
If you run
```
x = Input(shape=(seq_length, dim))
y = Conv1D(num_filts, 2, dilation_rate=8, padding="causal")(x)
print(y.shape)
```
Then the shape printed out will be `(?, seq_length, dim)`,…
-
I tried to understand it but I failed.
Please tell me why using it, thank you very much
-
Hi, thanks for open sourcing your code for the paper. Leveraging temporal convolutions is a great idea and the results are promising. However, I just want to point out an issue about the back-projecti…
-
I went through the #api channel and found our wishlists. Some of these may already be implemented in this repo and likely implemented _somewhere_ in our codes.
- [x] Numeric stability utilities to …
-
Hi Kizmuz, First of all congratulations for this really great job!
OK, I have trained my workers, and here you are some questions:
Do you have some code to test predictions with their model?
Do…
-
-
@yysijie @yjxiong hello, thank you for your sharing about the network, as a new student in this field, I want to ask you "how to add the temporal information in the graph ? " in the graph.py, i only s…
-
Will be doing a fair bit of playing with signal processing functions and Dask in the near term. Was thinking it would be nice to have a package (e.g. `dask-signal` or similar) with some common routine…
-
if i have many articles , they have different words. these articles maybe have some relationships. How can i integrate them?