-
## 🐛 Bug
Hi,
While working on some CTC extensions, I noticed that torch's CTCLoss was computing incorrect gradient. At least when using CPU (I have not tested on GPU yet). I observed this problem …
-
Hi,
any idea what's happening here?
I set width to 1000 instead of 4000 to rule out memory issues. I have a modern Mac.
```
(unity) fred@Freds-MacBook-Pro:~/unity/Fantasy_map_generator/Map g…
-
### Problem Description
Hi, everyone! I check the code of function `sampling_estimate`.
Assume we have a data instance `x` with `M` features.
- We keep the 1st to j-th feature as original, replace …
-
I have trained your model, but the results are just noisy image. And I found that the pose information in your code is just **random.randint**. I think this is why I just get noisy images.
And I r…
-
Hi,
I am trying to use WHD in order to optimize a semantic segmentation model. I have written this code:
import torch
from losses import *
whd = WeightedHausdorffDistance(resized_height = …
-
Hello! I would like to try out your C++ implementation of NNDescent because the PyNNDescent implementation does not fit into 1.5 TB of memory (my data matrix is 70,000,000 x 1024). Could you advise me…
-
Being able to simply do `data_frame.plot()` with Pandas-Bokeh is very handy and a huge productivity boost. Though currently there is no way to do multiple plots in a single plot to my understanding. …
-
https://github.com/alexis-jacq/LOLA_DiCE/blob/ec3f3f620a67df0a3e72f8e9227d09e4543dbb99/ipd_DiCE.py#L12-L22
@alexis-jacq Thanks a lot for such a readable implementation!
I ran LOLA-DiCE for num_looka…
vrn25 updated
2 years ago
-
To simplify things let's consider VGG16 based FCN-32s (not U-net):
Code:
```
def get_fcn_vgg16_32s(inputs, n_classes, h, w):
x = BatchNormalization()(inputs)
# Block 1
x = Conv2D(64, (3…
-
Hi,
I tried to run the glow gwas logistic regression but running into errors when writing out the results at the end:
Caused by: org.apache.spark.SparkException: Job aborted due to stage failur…