-
@AlexeyAB Hey,
Have you tried using INT8 for Max pooling layers? What is the reason you do not use INT8 for maxpool ?
Thanks in advance!
-
I find that [darknet53.conv.74](https://pjreddie.com/media/files/darknet53.conv.74) is not the same as [darknet53.weights](https://pjreddie.com/media/files/darknet53.weights) and [darknet53_448.weight…
-
有现成的onnx文件吗？类似于wespeaker在huggingface上的。我使用魔搭社区上面的[pt模型](https://www.modelscope.cn/models/iic/speech_charctc_kws_phone-wenwen/files)一直转换失败.
```
Traceback (most recent call last):
File "wekws/bin…
zmoth updated
6 months ago
-
Checklist of stuff we miss compared to [Deep Graph Library](https://docs.dgl.ai/api/python/nn.html).
PRs are welcome!
### Conv Layers
- [x] GraphConv (called `GCNConv` here)
- [ ] EdgeWei…
-
I've made an implementation of a fractional pooling layer, from http://arxiv.org/abs/1412.6071.
It seems to be working, although I haven't seen amazing results. If there's interest I can create a pul…
-
Hello @xbresson ,
Let me first thank for this work.
l went through your implementation. Hence , l have some question :
1- You set coarsening_levels = 4, however only L[0] and L[2] are used…
-
您好! 請問為何是local region 大小是4x4, 而不是3x3或是5x5呢?
是因為輸入圖片都resize 成256x256, 怕沒辦法算到每一塊嗎?
感謝!
-
### Describe the feature and motivation
It would be great to have a max/min pooling operation similar to pytorch's MaxPool layer. I'd imagine max and min pooling function that takes a kernel size, …
-
Hello author, in the config.py file, is the hop_lenth 256 instead of 32?
-
## 任务激励
- 达成任意一项任务即成为 Tengine 开源贡献者、活动贡献者认证证书；
- 根据达成任务的难度还有额外小礼品赠送
- 简单：T恤 + 多功能充电线
- 一般：T恤 + 多功能充电线 + 帽子
- 困难：T恤 + 多功能充电线 + 机械键盘
## 任务详情
### **算子类（C++- float32）**
此类算子添加参考文档 [如何快速添加…