-
Hi @dsindex
The new [BERT-Finetune](https://drive.google.com/file/d/1Vpt95HB-rOlI01OPZo00G0zizRkll67c/view?usp=sharing) model produces better results than the Luke benchmark. F1 score : 94.60 on C…
geo47 updated
3 years ago
-
I am a student who started my internship at graduate school and is building a new server.
I'm going to install bcbio according to the link recommended by the professor, but I run into the same prob…
-
Hi
Thanks for your good work, and congratulations.
I'm trying to figure out if it would be possible to run Vocals / Music separation in real time, with acceptable latency, on an ARM micro controller…
-
##### System information (version)
- OpenCV => 4.2
- Operating System / Platform => Ubuntu 18.04
- Compiler => clang++-6
##### Detailed description
In a test program where I was using ALT +…
-
Having trouble getting hasktorch going on nixos in the environment provided by
`nix-shell --arg cudaSupport true --argstr cudaMajorVersion 11 `
I can build hasktorch and setting `$DEVICE=cpu`, …
-
Hello,
I have trained a new network on my own dataset having input dimensions of 64x64x3 and with given topology
ifm = [64, 62, 30, 28, 13, 11]
ofm = [62, 60, 28, 26, 11, 9]
ifm_ch = [ 3, …
-
Hi @dsindex
Getting following error when using `--bert_use_subword_pooling`:
```
ntagger/model.py", line 737, in forward
embed_out = torch.cat([embed_out, pos_embed_out], dim=-1)
Runtime…
geo47 updated
3 years ago
-
This module leaks connections. How to reproduce:
I have the following code:
```
use LibCurl::Easy;
repeat while True {
my $content = LibCurl::Easy.new(URL => 'http://rss.cnn.com/rss/editio…
-
`__PREFIX(CNN_Construct)()` fails when `__PREFIX(CNN)(Input_1, Output_1)` is called anywhere in the application code. By commenting out the call to the CNN, the code runs successfully.
Below are s…
-
Hello,
With the given parameter, I applied CharCNN and concate with BERT embedding alongside POS embeddings. However, CharCNN concatination gives dimension error.
```
File "ntagger/model.py", l…
geo47 updated
3 years ago