update plot synthetic

Author: CharlieDinh

main_mnist.py

@@ -0,0 +1,15 @@
+#!/usr/bin/env python
+import h5py
+import matplotlib.pyplot as plt
+import numpy as np
+import argparse
+import importlib
+import random
+import os
+from flearn.servers.serveravg import FedAvg
+from flearn.servers.serverfedl import FEDL
+from flearn.trainmodel.models import *
+from utils.plot_utils import *
+import torch
+torch.manual_seed(0)
+

main_plot.py

@@ -0,0 +1,17 @@
+#!/usr/bin/env python
+import h5py
+import matplotlib.pyplot as plt
+import numpy as np
+import argparse
+import importlib
+import random
+import os
+from flearn.servers.serveravg import FedAvg
+from flearn.servers.serverfedl import FEDL
+from flearn.trainmodel.models import *
+from utils.plot_utils import *
+import torch
+torch.manual_seed(0)
+
+def main(dataset, algorithm, model, batch_size, learning_rate, hyper_learning_rate, L, num_glob_iters,
+         local_epochs, optimizer, clients_per_round, times):

plot_femnist.py

@@ -0,0 +1,19 @@
+#!/usr/bin/env python
+import h5py
+import matplotlib.pyplot as plt
+import numpy as np
+from utils.plot_utils import *
+import torch
+torch.manual_seed(0)
+
+algorithms_list = ["FEDL","FEDL","FEDL","FEDL","FEDL","FEDL","FEDL","FEDL","FEDL","FEDL","FEDL","FEDL"]
+rho = [1.4, 1.4, 1.4, 1.4,  2 ,2 , 2, 2, 5, 5, 5, 5]
+lamb_value = [0, 0, 0, 0,  0, 0, 0, 0 , 0, 0, 0 ,0]
+learning_rate = [0.04,0.04,0.04,0.04, 0.04,0.04,0.04,0.04, 0.04,0.04,0.04,0.04]
+hyper_learning_rate = [0.01,0.03,0.05,0.07, 0.01,0.03,0.05,0.07, 0.01,0.03,0.05,0.07]
+local_ep = [20, 20, 20, 20,  20, 20, 20, 20,  20, 20, 20, 20]
+batch_size = [0,0,0,0 ,0,0,0,0, 0,0,0,0]
+DATA_SET = "Linear_synthetic"
+number_users = 100
+
+plot_summary_linear(num_users=number_users, loc_ep1=local_ep, Numb_Glob_Iters=200, lamb=lamb_value, learning_rate=learning_rate, hyper_learning_rate = hyper_learning_rate, algorithms_list=algorithms_list, batch_size=batch_size, rho = rho, dataset=DATA_SET)

plot_mnist.py

@@ -28,12 +28,12 @@ def get_training_data_value(num_users=100, loc_ep1=5, Numb_Glob_Iters=10, lamb=[
             string_learning_rate = string_learning_rate + "_" +str(hyper_learning_rate[i])
         algorithms_list[i] = algorithms_list[i] + \
             "_" + string_learning_rate + "_" + str(num_users) + \
-            "u" + "_" + str(batch_size[i]) + "b"
+            "u" + "_" + str(batch_size[i]) + "b" + "_" + str(loc_ep1[i])
         if(rho[i] > 0):
             algorithms_list[i] += "_" + str(rho[i])+"p"
 
         train_acc[i, :], train_loss[i, :], glob_acc[i, :] = np.array(
-            simple_read_data(str(loc_ep1[i]) + "_avg", dataset + "_" + algorithms_list[i]))[:, :Numb_Glob_Iters]
+            simple_read_data("avg", dataset + "_" + algorithms_list[i]))[:, :Numb_Glob_Iters]
         algs_lbl[i] = algs_lbl[i]
     return glob_acc, train_acc, train_loss