WwZzz

已修复生成该benchmark任务时产生的bug并上传

在Client.unpack()里记录一份全局模型的副本self.received_global_model = copy.deepcopy(pakcage['model'])，在Client.pack中计算delta_model = model-self.received_global_model，然后对delta_model的参数进行额外的稀疏和量化，这种方式需要改动的地方较少

是的，我不小心在tutorial里写反了，然后只在知乎上改过来了，github忘了改了。谢谢你的提醒，马上修改。

Sorry, this is a bug when simultaneously using torch.multiprocessing and decorators in python. The 'spawn' mode is incompatible with the decorators. I have tried to search for a proper solution...

I've commented the decorators on `fedbase.BasicServer.communicate` ( i.e. `@ss.with_dropout` and `@ss.with_clock`), `fedbase.BasicClient.train` (i.e. only `@ss.with_completeness`) and `fedbase.BasicServer.communicate_with` (i.e. `@ss.with_latency`). After doing this, I run `main.py` with --num_threads 6, it seems...

> I've commented the decorators on `fedbase.BasicServer.communicate` ( i.e. `@ss.with_dropout` and `@ss.with_clock`), `fedbase.BasicClient.train` (i.e. only `@ss.with_completeness`) and `fedbase.BasicServer.communicate_with` (i.e. `@ss.with_latency`). After doing this, I run `main.py` with --num_threads 6, it...

> I've commented the decorators on `fedbase.BasicServer.communicate` ( i.e. `@ss.with_dropout` and `@ss.with_clock`), `fedbase.BasicClient.train` (i.e. only `@ss.with_completeness`) and `fedbase.BasicServer.communicate_with` (i.e. `@ss.with_latency`). After doing this, I run `main.py` with --num_threads 6, it...

> > I've commented the decorators on `fedbase.BasicServer.communicate` ( i.e. `@ss.with_dropout` and `@ss.with_clock`), `fedbase.BasicClient.train` (i.e. only `@ss.with_completeness`) and `fedbase.BasicServer.communicate_with` (i.e. `@ss.with_latency`). After doing this, I run `main.py` with --num_threads 6,...