-
LeNet model used,
Traceback (most recent call last):
File "main.py", line 155, in
optimizer = optim.SGD(model.parameters(), lr=args.lr, momentum=args.momentum)
File "/usr/local/lib/python…
eeric updated
2 years ago
-
when i put centerloss's parameters into optimizer, raise valueError("optimizer got an empty parameter list")
optimizer_centloss = torch.optim.SGD(criterion_cent.parameters(), lr=args.lr_cent)
-
## How pytorch optimizer work?
https://mcneela.github.io/machine_learning/2019/09/03/Writing-Your-Own-Optimizers-In-Pytorch.html
, 60 bias
DP not recommended, instead use torch.distributed.run for best DDP Multi-GPU results.
See Multi-GPU Tutorial at https://…
-
I tested three methods in a very simple problem, and got the result as above.
Code a…
-
### 🐛 Describe the bug
I'm using `flyte` to reproduce the token throughput and memory savings results reported in this [repo's README](https://github.com/linkedin/Liger-Kernel?tab=readme-ov-file#su…
-
### bug描述 Describe the Bug
使用Paddle-gpu 20241016的daily包，运行下述代码出现如下报错，使用Paddle-gpu 3.0beta则可以正常运行。
测试代码:
im…
-
# Optimizers
- 可以先实例化一个优化器对象，然后将它传入model.compile()，如下示例:
```
sgd = optimizers.SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='mean_squared_error', optimizer=sgd)
```
-…
-
Why does running pFedSim and FedAvg using the medmnistA dataset in your latest repository result in severe fluctuations and non-convergence? This issue didn't occur in previous repositories. Could it …