About the implementation of Fed.py

[szbonaldo]

I think it's wrong when the data distribution is noniid, should change to:
def FedAvg(w, dict_len):
w_avg = copy.deepcopy(w[0])
for k in w_avg.keys():
w_avg[k] = w_avg[k] * dict_len[0]
for i in range(1, len(w)):
w_avg[k] += w[i][k] * dict_len[i]
w_avg[k] = w_avg[k] / sum(dict_len)
return w_avg
Which dict_len is a list contains number of samples in each clients.

[baicaihenxiao]

yes.
I think the author do not consider weight in this function because all users own the same amount of samples and are set to the same weight.