jacobian

commit 58dab65b73329cbb51485c00b420846b8445785f
parent 9d0599d64aba88854b603dbc39aadc7a262729d4
Author: David Freifeld <freifeld.david@gmail.com>
Date:   Fri,  3 Jul 2020 22:58:03 -0700

Updated scripts to try and work w/ strassen

Diffstat:
A
benchmark.py
 | 
31
+++++++++++++++++++++++++++++++
M
example.cpp
 | 
7
++++++-
M
example.py
 | 
33
---------------------------------

3 files changed, 37 insertions(+), 34 deletions(-)
diff --git a/benchmark.py b/benchmark.py
@@ -0,0 +1,31 @@
+import mrbpnn
+import matplotlib.pyplot as plt
+import numpy
+import time
+
+def bench(batch_sz, layers):
+    init = time.time()
+    net = mrbpnn.Network("./data_banknote_authentication.txt", batch_sz, 0.0155, 0.03, 0.9)
+    net.add_layer(4, "linear")
+    for i in range(layers):
+        net.add_layer(5, "relu")
+    net.add_layer(1, "resig")
+    net.initialize()
+    initend = time.time()
+    net.train(50)
+    end = time.time()
+    return (end-init)
+
+x = []
+y = []
+i = 1
+while(i < 1340):
+    print(i)
+    y.append(bench(i, 1))
+    x.append(i)
+    i+=1;
+plt.plot(x,y, label = "ML-in-Parallel (Sequential)")
+    
+# plt.plot(otherlist, [2.3994078636169434, 1.2735769748687744, 1.0030598640441895, 0.8972160816192627, 0.801548957824707, 0.752018928527832, 0.7073678970336914, 0.6857280731201172, 0.6707980632781982, 0.6421489715576172, 0.6614980697631836, 0.6403779983520508, 0.7251319885253906, 0.6796879768371582, 0.6601080894470215, 0.6711599826812744, 0.6432759761810303, 0.6491389274597168, 0.6762490272521973, 0.6859049797058105, 0.7067179679870605, 0.7142889499664307, 0.7258059978485107, 0.7868969440460205, 0.7326970100402832, 0.7365641593933105, 0.7576079368591309, 0.7772500514984131, 0.8062641620635986, 0.7768490314483643, 0.8253629207611084, 0.8264601230621338, 0.8459320068359375, 0.9670729637145996, 0.8388969898223877, 0.9129719734191895, 0.9009649753570557, 0.8916170597076416, 0.8926799297332764, 0.9171609878540039, 0.9242072105407715, 0.9534740447998047, 0.947465181350708, 0.9723358154296875, 1.018247127532959, 1.1208629608154297, 1.014026165008545, 1.034980058670044, 1.0626468658447266, 1.080394983291626, 1.0627479553222656, 1.0839190483093262, 1.0938241481781006, 1.127730131149292, 1.1265759468078613, 1.136888027191162, 1.140428066253662, 1.1712510585784912, 1.206390142440796, 1.2087180614471436, 1.4066569805145264, 1.2425589561462402, 1.280066967010498, 1.2891559600830078, 1.3243582248687744, 1.3152379989624023], label="Keras")
+plt.legend()
+plt.show()
diff --git a/example.cpp b/example.cpp
@@ -13,10 +13,15 @@ double bench(int batch_sz)
   net.initialize();
   net.train(50);
   auto end = std::chrono::high_resolution_clock::now();
+  //  net.list_net();
   return std::chrono::duration_cast<std::chrono::nanoseconds>(end - start).count() / pow(10,9);
 }
 
 int main()
 {
-  bench(10);
+  bench(50);
+  bench(50);
+  bench(50);
+  bench(50);
+  bench(50);
 }
diff --git a/example.py b/example.py
@@ -4,36 +4,6 @@ import matplotlib.pyplot as plt
 import numpy
 import time
 import wandb
-from viznet import NodeBrush, EdgeBrush, DynamicShow
-
-def draw_feed_forward(ax, num_node_list):
-    '''
-    draw a feed forward neural network.
-
-    Args:
-        num_node_list (list<int>): number of nodes in each layer.
-    '''
-    num_hidden_layer = len(num_node_list) - 2
-    token_list = ['\sigma^z'] + \
-        ['y^{(%s)}' % (i + 1) for i in range(num_hidden_layer)] + ['\psi']
-    kind_list = ['nn.input'] + ['nn.hidden'] * num_hidden_layer + ['nn.output']
-    radius_list = [0.3] + [0.2] * num_hidden_layer + [0.3]
-    y_list = 1.5 * np.arange(len(num_node_list))
-
-    seq_list = []
-    for n, kind, radius, y in zip(num_node_list, kind_list, radius_list, y_list):
-        b = NodeBrush(kind, ax)
-        seq_list.append(node_sequence(b, n, center=(0, y)))
-
-    eb = EdgeBrush('-->', ax)
-    for st, et in zip(seq_list[:-1], seq_list[1:]):
-        connecta2a(st, et, eb)
-
-
-def real_bp():
-    with DynamicShow((6, 6), '_feed_forward.png') as d:
-        draw_feed_forward(d.ax, num_node_list=list)
-
 
 batch_sz = 10
 layers = 1
@@ -72,6 +42,3 @@ end = time.time()
     
 wandb.run.summary["time"] = end-init
 wandb.save('jacobian.h5')
-
-with DynamicShow((6, 6), '_feed_forward.png') as d:
-        draw_feed_forward(d.ax, num_node_list=layers_list)