-
Dear Aayush Ankit,
Thank you for your work.
When I compile the VGG-16 model with the puma-compiler, it crashes due to the constantly increasing memory during the 3rd step `coalescer`, which will…
-
-
### System information
- I was trying to train standard CNN network
- OS Platform: Windows 10
- TF installed via Anaconda - standard release
- TF2.3.1 latest release
- Python 3.6.12
…
-
There is a problem when using TWBlue as a Japanese user.
In Twitter JP rules, Japanese characters are counted as one character, ascii character is counted as 0.5, with the maximum of 140. Since the …
yncat updated
3 years ago
-
I have the following code:
lr_multipliers = {'lstm_1': 0.5}
optimizer = AdamW(lr=1e-4, model=model_AdamW, lr_multipliers=lr_multipliers,
use_cosine_annealing=True, total_iterati…
-
## Instructions To Reproduce the 🐛 Bug:
1. Full runnable code or full changes you made:
```
If making changes to the project itself, please use output of the following command:
git rev-parse HEAD;…
-
Hi,
I think your code may have some problems about data split and model:
1. In line 101 of semi_supervised.py, 0.2 may be means percentage? I think you should use args.percentage.
2. In super…
-
Trying to render in CC65 this simple BASIC loop:
10 open 5,2,3,chr$(6): rem chr$(6) = 300 baud
20 get#1,a$ : print a$; : get a$ : print #1,a$;
30 goto 20
But it happens that **cbm_…
-
**Describe the bug**
Sentiment scores fluctuate on resubmission of the same text. It changes the score of one particular sentence from negative to neutral upon repeated calls.
**To Reproduce**
St…
-
We were getting OOMs in LR and I managed to confidently bisect down to the commit where #11188 was merged. (its `core(image-elements): collect CSS sizing, ShadowRoot, & position`)
```sh
node ligh…