-
按照Readme中的方法将Conv2d替换后，是必须要重新训练或者finetune吗？
如果我要加载已经训练好的模型，这会有影响吗
谢谢
-
上次我发的报错是因为参数是cpu模式下的，这次的我在cuda模式下，将pytorch模型转换成了onnx然后再尝试使用x2paddle时产生了新的报错
## 问题描述
…
-
感谢您参与 X2Paddle 社区！ 问题模版为了 X2Paddle 能更好的迭代，例如新功能发布、 RoadMaps 和错误跟踪. :smile_cat:
## 问题描述
File "pd_model\x2paddle_code.py", line 56, in forward
x2paddle_onnx__Mul_377 = paddle.su…
-
Hello! Thanks so much for your submission! Just wanted to confirm that we've received your entry. Looking forward to diving into your results!
Trevor
-
Hello! Thanks so much for your submission! Just a couple of points:
1. We do request that entries include the code necessary to reproduce their results. It looks like you've included an evaluation …
-
### Checklist
- [X] I've looked through the [README](https://github.com/react-scheduler/react-big-schedule#readme)
- [X] I've verified that I'm running react-big-schedule version **4.2.0**
- [X] I've…
-
I used the code, compiled with Arduino from branch gnss_compass together mn 100-2 display as a master, hull transducer for temp, speed and depth. In short form following remarks:
- Switch on sequence…
-
请问作者的模型大小对比图怎么得到的，我每次改变量化bit后保存的模型大小都一样
-
Hello! Thanks so much for your entry!
When I try to run eval, I get errors load the weight_path. It looks like you have a local path hardcoded into the script there. Is that file available in this…
-
Hi~首先非常感谢你的工作。我最近将micronet的dorefa量化部分适用到我的工程中（检测模型），发现几个问题，希望讨论一下：
1. load预训练的浮点模型，使用dorefa的量化inference模式，检测精度直接降为0，求问为什么精度损失会这么大？
2. 采用dorefa的qat模式，正常训练后精度接近于原float模式，但是load预训练模型与不load的结果并没有区别，这是为…