unrelevant changes related to experiments. build_command_line_array shouldn't...

unrelevant changes related to experiments. build_command_line_array shouldn't bu used anymore + changes in drawgraphes relative to cifar10 experiment

main/experiments/build_command_line_array.py

 import numpy as np
 import math
+
 if __name__ == '__main__':
-    batch_size = np.logspace(3, 9, dtype=int, base=2, num=5)
-    num_epoch = 50
-    sigma = 5.0
-    gamma = 0.003
-    subsample_size = np.logspace(3, 9, dtype=int, base=2, num=5)
+    raise DeprecationWarning("This should not be used, lazygrid of skluc should be used instead")
+
+    batch_size = np.logspace(3, 9, dtype=int, base=2, num=4)
+    num_epoch = 100
+    # sigma = np.logspace(-1, 2, base=10, num=3)
+    sigma = [1]
+    # gamma = np.logspace(-4, 0, base=10, num=3)
+    gamma = [1]
+    subsample_size = np.logspace(3, 9, dtype=int, base=2, num=4)
     networks_types = ["dense", "deepfriedconvnet", "deepstorm"]
-    datasets = ["mnist",
-                "cifar"]
+    datasets = ["cifar"]
     output_dense = 2048
-    nys_layer_dim_out = np.logspace(3, int(math.log(output_dense, 2)), dtype=int, base=2, num=5)
+    nys_layer_dim_out = np.logspace(3, int(math.log(output_dense, 2)), dtype=int, base=2, num=3)
     for d in datasets:
         for network in networks_types:
             s_network = network + " " + "--" + str(d) + " " + "--time" + " " + "--test" + " " + "-e" + " " + str(num_epoch) + " "
             for b_size in batch_size:
                 s_epoch = s_network + "-s " + str(b_size) + " "
                 if network == "deepfriedconvnet":
-                    s_sigma = s_epoch + "-S " + str(sigma) + " "
-                    print(s_sigma)
+                    for sig in sigma:
+                        s_sigma = s_epoch + "-S " + "{:.5f}".format(sig)
+                        print(s_sigma)
                 elif network == "deepstorm":
-                    s_gamma = s_epoch + "-G " + str(gamma) + " "
-                    for nys_size in subsample_size:
-                        s_nys = s_gamma + "-m " + str(nys_size) + " "
-                        for nys_output_size in nys_layer_dim_out:
-                            s_nys_out = s_nys + "-w" + " " + str(nys_output_size)
-                            print(s_nys_out)
+                    for gam in gamma:
+                        s_gamma = s_epoch + "-G " + "{:.5f}".format(gam) + " "
+                        for nys_size in subsample_size:
+                            s_nys = s_gamma + "-m " + str(nys_size) + " "
+                            for nys_output_size in nys_layer_dim_out:
+                                s_nys_out = s_nys + "-w" + " " + str(nys_output_size)
+                                print(s_nys_out)
                 else:
                     print(s_epoch)
-                    pass
\ No newline at end of file
+                    pass

main/experiments/draw_graphes.py

@@ -5,11 +5,13 @@ import pandas as pd
 
 pd.set_option('display.width', 1000)
 
-DIRNAME = "/home/luc/PycharmProjects/deepFriedConvnets/main/results_global5"
+DIRNAME = "/home/luc/Resultats/Deepstrom/CIFAR10/v2/100_epochs"
 FILENAME = "gathered_results"
 
-batch_size = np.logspace(3, 9, dtype=int, base=2, num=5)
-subsample_size = np.logspace(3, 9, dtype=int, base=2, num=5)
+batch_size = np.logspace(3, 9, dtype=int, base=2, num=4)
+# batch_size = np.logspace(3, 9, dtype=int, base=2, num=5)
+subsample_size = np.logspace(3, 9, dtype=int, base=2, num=4)
+# subsample_size = np.logspace(3, 9, dtype=int, base=2, num=5)
 
 if __name__ == '__main__':
     filepath = os.path.join(DIRNAME, FILENAME)
@@ -25,9 +27,10 @@ if __name__ == '__main__':
                    "deepstrom_dim"]
 
     df = pd.read_csv(filepath, names=field_names)
-    df = df[df["dataset"] == "mnist"]
+    # df = df[df["dataset"] == "mnist"]
+    df = df[df["dataset"] == "cifar"]
 
-    nrows = 3
+    nrows = 2
     ncols = 2
     f, axxarr = plt.subplots(nrows, ncols)
     f2, axxarr2 = plt.subplots(nrows, ncols)
@@ -48,9 +51,9 @@ if __name__ == '__main__':
             df_batch_size_deepfriedconvnet = df_batch_size[df_batch_size["method_name"] == "DeepFriedConvnet"]
             df_batch_size_deepstrom_runtime_sort = df_batch_size_deepstrom.sort_values(by=["runtime"])
             axxarr[i][j].set_title("batch size = {}".format(curr_batch_size))
-            axxarr[i][j].plot(df_batch_size_deepstrom_runtime_sort["runtime"],
+            axxarr[i][j].scatter(df_batch_size_deepstrom_runtime_sort["runtime"],
                               df_batch_size_deepstrom_runtime_sort["accuracy"],
-                              label="Deepstrom")
+                              label="Deepstrom", marker="x")
             axxarr[i][j].scatter(df_batch_size_dense["runtime"],
                                  df_batch_size_dense["accuracy"], color="r",
                                  label="Dense",
@@ -59,7 +62,7 @@ if __name__ == '__main__':
                                  df_batch_size_deepfriedconvnet["accuracy"], color="g",
                                  label="DeepFriedConvnet",
                                  marker="x")
-            axxarr[i][j].legend(loc="lower right")
+            # axxarr[i][j].legend(loc="lower right")
 
             curr_batch_size_idx += 1
 
@@ -68,9 +71,9 @@ if __name__ == '__main__':
             # print(df_batch_size_deepstrom)
             # print(df_batch_size_deepstrom_subsample_sort)
             axxarr2[i][j].set_title("batch size = {}".format(curr_batch_size))
-            axxarr2[i][j].plot(df_batch_size_deepstrom_subsample_sort["subsample_size"],
+            axxarr2[i][j].scatter(df_batch_size_deepstrom_subsample_sort["subsample_size"],
                                df_batch_size_deepstrom_subsample_sort["accuracy"],
-                               label="Deepstrom")
+                               label="Deepstrom", marker="x")
             nb_val = len(df_batch_size_deepstrom_subsample_sort["subsample_size"])
             axxarr2[i][j].plot(df_batch_size_deepstrom_subsample_sort["subsample_size"],
                                [df_batch_size_dense["accuracy"].values[0] for _ in range(nb_val)], color="r",
@@ -85,9 +88,9 @@ if __name__ == '__main__':
             for k, nys_dim in enumerate(subsample_size):
                 df_batch_size_deepstrom_nys_dim = df_batch_size_deepstrom[df_batch_size_deepstrom["subsample_size"] == nys_dim]
                 df_batch_size_deepstrom_nys_dim_sort = df_batch_size_deepstrom_nys_dim.sort_values(by=["deepstrom_dim"])
-                axxarr3[k].plot(df_batch_size_deepstrom_nys_dim_sort["deepstrom_dim"],
+                axxarr3[k].scatter(df_batch_size_deepstrom_nys_dim_sort["deepstrom_dim"],
                                 df_batch_size_deepstrom_nys_dim_sort["accuracy"],
-                                label="Deepstrom")
+                                label="Deepstrom", marker="x")
                 nb_val = len(df_batch_size_deepstrom_nys_dim_sort["deepstrom_dim"])
                 axxarr3[k].plot(df_batch_size_deepstrom_nys_dim_sort["deepstrom_dim"],
                                 [df_batch_size_dense["accuracy"].values[0] for _ in range(nb_val)], color="r",