-
我做了一个简单的测试，我使用了X2Paddle里的optimzer.Adam，首先用w的参数创建优化器，然后使用optimzer.add_param_group()添加b的参数，训练前后w的参数更新了，但b的参数没有更新，这是怎么回事呢？
如下是结果和代码：
`
This is how I define my_loss:
```python
def my_loss(y_pred, y_true):
with tf.name_scop…
-
I understand the concept of DenseLoss/weights broadly. But to practically use it do I just specify the weights computed by DenseWeight in the 'loss_weight' parameter while compiling the model or is th…
-
欢迎您反馈PaddleHub使用问题，非常感谢您对PaddleHub的贡献！
在留下您的问题时，辛苦您同步提供如下信息：
1. paddlehub版本2.3.0，代码在项目中公开，[《华为车道检测》](https://aistudio.baidu.com/aistudio/projectdetail/4531250)。主要代码：
import paddlehub as hub
mo…
-
## ❓ Questions & Help
Hi! I am trying to train a GAE to obtain embeddings of a graph.
Here is my code. The "data" only includes feature matrix "x" and edge index "edge_index". The loss is alway…
-
Currently, `gp.util.train` return the trace over loss (loss v/s iterations)
`losses = gp.util.train(vsgp, num_steps=num_steps)`
If one needs to get a trace over other quantities, say kernel para…
-
Hello @Eromera Thank you so much for your work. I have a problem while running your code using the newest version of pytorch. As mentioned by pytorch that `optimizer.step()` should be called before` l…
-
https://github.com/microsoft/DeepSpeed/issues/998 tackles the `aio` param section, but we still have no user guide for the new "offload_optimizer" and "offload_param" sections. We have:
```
…
-
Hi, @16lemoing,
Congratulations on your paper acceptance! :tada:
I encountered some problems while reproducing your training results. I followed the instructions in [training](https://github.com…