From 176ed663c1251037dd94397287921e9316fe4c09 Mon Sep 17 00:00:00 2001
From: romanamo <r-schoene@gmx.net>
Date: Thu, 9 May 2024 01:12:49 +0200
Subject: [PATCH] finalized code + cleanup
---
uebungen/uebung3.py | 86 ++++++++++++++++++++++++++-------------------
1 file changed, 49 insertions(+), 37 deletions(-)
diff --git a/uebungen/uebung3.py b/uebungen/uebung3.py
index 5aa1627..f65dd85 100644
--- a/uebungen/uebung3.py
+++ b/uebungen/uebung3.py
@@ -1,5 +1,3 @@
-from typing import Tuple
-
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
@@ -7,95 +5,109 @@ import matplotlib.pyplot as plt
def load_data():
df_orig_train = pd.read_csv('mnist_test_final.csv')
- df_digits = df_orig_train.drop('label',axis=1)
+ df_digits = df_orig_train.drop('label', axis=1)
return df_digits.to_numpy()
+
mnist = load_data()
+
def sigmoid(x):
return 1.0 / (1.0 + np.exp(-x)) # Sigmoidfunktion
+
class RBM:
- def __init__(self, visible_size: int, hidden_size: int, learnrate: float=0.1) -> None:
+ def __init__(self, visible_size: int, hidden_size: int, learnrate: float = 0.1, epochs=20):
+ """__init__ Initializes a newly created Ristricted Bolzmann Machine.
+
+ Args:
+ visible_size (int): amount of neurons inside the visible layer
+ hidden_size (int): amount of neurons inside the hidden layer
+ learnrate (float, optional): learnrate eta in [0;1]. Defaults to 0.1.
+ epochs (int, optional): training epochs. Defaults to 20.
+ """
self.learnrate = learnrate
self.visible_size = visible_size
self.hidden_size = hidden_size
- self.k = 2
- self.epochs = 10
+ self.epochs = epochs
self.reset()
- def reset(self) -> None:
+ def reset(self):
+ # initialize/reset learnable attributes
self.weights = np.random.randn(self.visible_size, self.hidden_size)
self.visible_bias = np.zeros(self.visible_size) * 0.1
self.hidden_bias = np.zeros(self.hidden_size) * 0.1
def activate(self, v0):
return sigmoid(np.matmul(v0.T, self.weights) + self.hidden_bias)
-
+
def reactivate(self, h0):
return sigmoid(np.matmul(self.weights, h0.T) + self.visible_bias)
-
+
def contrastive_divergence(self, v0, h0, v1, h1):
+ # calculate gradients
postive_gradient = np.outer(v0, h0)
negative_gradient = np.outer(v1, h0)
+ # Adjust weights by delta
self.weights += self.learnrate * (postive_gradient - negative_gradient)
- return self.weights
-
+ # Adjust biases by delta
+ self.visible_bias += self.learnrate * (v0 - v1)
+ self.hidden_bias += self.learnrate * (h0 - h1)
+
def train(self, v0):
for _ in range(self.epochs):
- h0 = self.activate(v0) # Aktivieren versteckter Schicht
- v1 = self.reactivate(h0) # Reaktivieren sichtbarer Schicht
+ # activate hidden layer
+ h0 = self.activate(v0)
+
+ # reactivate visible layer
+ v1 = self.reactivate(h0)
+
+ #activate next hidden layer
h1 = self.activate(v1)
+ # Adjust weights
self.contrastive_divergence(v0, h0, v1, h1)
-
- self.visible_bias += self.learnrate * (v0 - v1)
- self.hidden_bias += self.learnrate * (h0 - h1)
-
- return h0, v1
-
- def run(self, v0 : np.ndarray) -> Tuple[np.ndarray, np.ndarray]:
- """run Runs the Restricted Boltzmann machine on some input vector v0.
-
- Args:
- v0 (np.ndarray): 1-dimensional Input vector
-
- Returns:
- Tuple[np.ndarray, np.ndarray]: (hidden activation, visible reactivation)
- """
+ def run(self, v0):
+ # activate hidden layer
h0 = self.activate(v0)
v1 = self.reactivate(h0)
return h0, v1
+rbm = RBM(28**2, 256, 0.1, epochs=3)
def validate(idx):
-
+ #flatten and normalize mnist data
test = mnist[idx].flatten()/255
+
+ # train bolzmann machine and run
rbm.train(test)
(hid, out) = rbm.run(test)
- return (hid.reshape((5, 5)), out.reshape((28,28)))
+ return (hid.reshape((16, 16)), out.reshape((28, 28)))
-
-rbm = RBM(28**2, 25, 0.1)
-
-rows, columns = (4,4)
+# plot results
+rows, columns = (4, 6)
fig = plt.figure(figsize=(10, 7))
+
for i in range((rows * columns)):
if i % 2 == 0:
(hid, out) = validate(i)
- fig.add_subplot(rows, columns, i+1)
+
+ # hidden layer
+ fig.add_subplot(rows, columns, i+1)
plt.imshow(hid, cmap='gray')
- fig.add_subplot(rows, columns, i+2)
+ plt.axis('off')
+
+ # visible layer
+ fig.add_subplot(rows, columns, i+2)
plt.imshow(out, cmap='gray')
plt.axis('off')
plt.show()
-