-
Hi @taesungp , great project ! I have a question that in your paper and demo video you show that the model can change the region in the object using PCA collaborate with the mask user draw. Can you ex…
-
I encountered bn configs failing on gfx908 while using the develop branch. Here are sample configs that failed (these are not all)
./bin/MIOpenDriver bnormfp16 -n 256 -c 64 -H 112 -W 112 -m 1 --forw …
-
A while back on my Welsh course, I clicked the button that has the fly-over hint "View the expanded list of solutions, including all automatically generated variants. More exhaustive but more readable…
TNG02 updated
3 months ago
-
I use the Lightroom plugin from https://github.com/ftischhauser/JPEGOptimizer/ which uses jpeg-recompress. As part of my export process I have jpeg recompression enabled, and it is failing reliably on…
-
添加mae_layer, ordianl_regression_loss_layer的步骤：
1，将mae_layer.hpp, ordinal_regression_loss_layer.hpp 放置在caffe/include/caffe/layers/下
2，将mae_layer.cpp, ordinal_regression_loss_layer.cpp, ordinal_regres…
-
### 请提出你的问题 Please ask your question
请问是否可以对paddle推理模型进行节点的删除、添加、属性修改等操作？谢谢！
-
there are many is None or is not None in
https://github.com/huggingface/transformers/blob/master/src/transformers/modeling_bert.py, for example:
https://github.com/huggingface/transformers/blob/mas…
-
@lauranoren points out that we should gather stories and use them to illustrate points.
-
Hi, I found that the loss used in this repo is a cross-entropy loss between prediction and mask.
`loss = F.binary_cross_entropy_with_logits(pred, mask)`
But the loss mentioned in the paper is a …
-
## Background
We are evaluating how to build a new backend on triton, But there is a problem, that is, there are some relatively coarse-grained instructions on our hardware, such as convolution, an…