-
您好，请问是还有其他什么训练策略么？训练了几次均复现不出论文中的精度，S measure 连69都没超过
-
### Description
### Expected behavior with the suggested feature
- [ ] [ContraRec: "Sequential Recommendation with Multiple Contrast Signals" Wang et al., TOIS'2022.](https://github.com/TH…
-
Hi,
I followed https://wiki.loliot.net/docs/lang/python/libraries/yolov4/python-yolov4-edge-tpu/ to train a model with only one class.
If I use the original yolov4-tiny.cfg, the training works no…
-
CVPR2021的分类中，点云分类下：
[15] PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds(PAConv：点云上具有动态内核组装的位置自适应卷积)
这篇的code链接请改为：
https://github.com/CVMI-Lab/PAConv
Thank…
-
### Describe the bug
I want to convert a unet to onnx using the way as [example](https://github.com/huggingface/diffusers/blob/main/scripts/convert_stable_diffusion_checkpoint_to_onnx.py), i can get …
-
Hi, thank you for providing this nice implementation.
[Here](https://github.com/GrumpyZhou/pytorch-dgcnn/blob/master/networks/dgcnn.py#L75) in the classification network, it seems to me that you c…
-
Hi. I'm trying using torch2trt_dynamic to convert models from torch to trt. I got an unexpected issue.
To reproduce it I use lenet5 like neural network.
```
from torch2trt_dynamic import torch2trt_…
-
Excellent work !!!
Recently I have studied your paper and code , which is very enlightening to me. I sincerely think that your work is of great significence for us to study the dynamic convolution…
-
### 🐛 Describe the bug
There are following issues:
1. passing `Parameter` as argument instead of `Tensor` causes recompilation
2. setting `torch._dynamo.mark_dynamic` on `Parameter` has no effe…
-
Cant make it work.
I have sequence of vectors size 240 as features and one label per sequence; so this is sequence-to-one.
Simple LSTM setup with `BS.Sequences.Last` and dynamic axis works OK.
But,…