-
Hi! I am wondering how I could get spatial distributions (specifically, for earthquakes) similar to those in Figure 7 of your paper. I guess I should use the `sample()` or `p_sample_loop()` method, bu…
-
I'd like to propose adding a new value to the `shape-outside` property of `line-box`. This would enable floating a title or other block of text and allowing text to wrap around it following the contou…
-
`(base) :~/loss/SegLossBias/tests$ python test_compound_losses.py
Traceback (most recent call last):
File "~/SegLossBias/tests/test_compound_losses.py", line 5, in
from seglossbias.modeling…
-
**Describe the bug**
Conv2D Frop gives wrong output when calculating a small conv in FP32
**Steps/Code to reproduce bug**
Simply run
```
import torch
import numpy as np
import cutlass
inpu…
-
In my computer(A5000 card), it takes 19G VRAM. is it possible to reduce it?
here is my code:
```
# from AUTOMATC1111
# maybe modified by Nyanko Lepsoni
# modified by crosstyan
import os.path
im…
-
I want to know how to use your code.
This is my code
`import tensorflow as tf
import numpy as np
import os
from PIL import Image
import random
import math
import torch
import torch.nn as nn
…
-
**Is your feature request related to a problem? Please describe.**
It is not possible to use the output (NodeCollection) of SelectNodesByMask() as an input to DumpLayerConnections().
**Describe th…
-
I have some problem when I use centerloss in image classification with keras.
1、in **custom_vgg_model.fit(y = {'fc2':y_train,'predictions':y_train})**,'fc2':y_train have error that
```
ValueError: …
-
## Description
Due to #1802, if you use `out=myblockoperator.domain_geometry().allocate(0)` where `myblockoperator` is a BlockOperator of size (1,1) then out will be a DataContainer and not a Block…
-
I would like to modify the critic of the Network with the purpose of not only working as a discriminator but also as an auxiliar classifier. Therefore, I would like the last layer of the critic to out…