refactor: code de-dup

.gitignore

@@ -1,3 +1,4 @@
 __pycache__
 *.pyc
 .venv
+mnist.npz

autoencoder.py

@@ -1,74 +1,21 @@
 import numpy as np
-from utils import (regularize,
+from utils import (dynamic_loss_plot_init,
-                   dynamic_loss_plot_init,
                    dynamic_loss_plot_update,
                    dynamic_loss_plot_finish)
-import types
 from tqdm import tqdm
+from layers import NNLayer
 
 LOADER = ['⡿', '⣟', '⣯', '⣷', '⣾', '⣽', '⣻', '⢿']
 
 
-class Encoder:
-    def __init__(self,
-                 in_size: int,
-                 out_size: int,
-                 lr: float,
-                 activation_func: types.FunctionType):
-        self.W = np.random.uniform(-1, 1, (in_size, out_size))
-        self.B = np.zeros((out_size))
-        self.lr = lr
-        self.last_input = None
-        self.last_output = None
-        self.activation_func = activation_func
-
-    def forward(self, V: np.ndarray) -> np.ndarray:
-        self.last_input = V
-        res = V @ self.W + self.B
-        self.last_output = regularize(self.activation_func(res))
-        return self.last_output
-
-    def backprop(self, error: np.ndarray):
-        dW = np.outer(self.last_input, error)
-        self.W -= self.lr * dW
-        self.B -= self.lr * error
-        return error @ self.W.T
-
-
-class Decoder:
-    def __init__(self,
-                 in_size: int,
-                 out_size: int,
-                 lr: float,
-                 activation_func):
-        self.W = np.random.uniform(-1, 1, (in_size, out_size))
-        self.B = np.zeros((out_size))
-        self.lr = lr
-        self.last_input = None
-        self.last_output = None
-        self.activation_func = activation_func
-
-    def forward(self, V: np.ndarray) -> np.ndarray:
-        self.last_input = V
-        res = V @ self.W + self.B
-        self.last_output = regularize(self.activation_func(res))
-        return self.last_output
-
-    def backprop(self, error: np.ndarray):
-        dW = np.outer(self.last_input, error)
-        self.W -= self.lr * dW
-        self.B -= self.lr * error
-        return error @ self.W.T
-
-
 class Autoencoder:
     def __init__(self,
                  in_len: int,
                  bottleneck: int,
                  lr: float,
                  activation_func):
-        self.encoder = Encoder(in_len, bottleneck, lr, activation_func)
+        self.encoder = NNLayer(in_len, bottleneck, lr, activation_func)
-        self.decoder = Decoder(bottleneck, in_len, lr, activation_func)
+        self.decoder = NNLayer(bottleneck, in_len, lr, activation_func)
 
     def train(self, v: np.ndarray) -> float:
         encoded = self.encoder.forward(v)
@@ -92,7 +39,7 @@ class Autoencoder:
         with tqdm(bar_format="{desc} {elapsed} {rate_fmt}") as lbar:
             while True:
                 lbar.set_description(
-                    f"{LOADER[epoch % len(LOADER)]} Training ({epoch=} error={prev_error:.2f})",
+                    f"{LOADER[epoch % len(LOADER)]} Training ({epoch=} error={prev_error:.2f})", # noqa
                 )
                 lbar.update()
                 error = 0

layers.py

@@ -0,0 +1,29 @@
+import numpy as np
+import types
+from utils import regularize
+
+
+class NNLayer:
+    def __init__(self,
+                 in_size: int,
+                 out_size: int,
+                 lr: float,
+                 activation_func: types.FunctionType):
+        self.W = np.random.uniform(-1, 1, (in_size, out_size))
+        self.B = np.zeros((out_size))
+        self.lr = lr
+        self.last_input = None
+        self.last_output = None
+        self.activation_func = activation_func
+
+    def forward(self, V: np.ndarray) -> np.ndarray:
+        self.last_input = V
+        res = V @ self.W + self.B
+        self.last_output = regularize(self.activation_func(res))
+        return self.last_output
+
+    def backprop(self, error: np.ndarray):
+        dW = np.outer(self.last_input, error)
+        self.W -= self.lr * dW
+        self.B -= self.lr * error
+        return error @ self.W.T

mnist_test.py

@@ -9,7 +9,7 @@ def load_mnist():
     import requests
 
     mnist_path = "./mnist.npz"
-    mnist_url = "https://storage.googleapis.com/tensorflow/tf-keras-datasets/mnist.npz"
+    mnist_url = "https://storage.googleapis.com/tensorflow/tf-keras-datasets/mnist.npz"  # noqa
     if not os.path.exists(mnist_path):
         with open(mnist_path, "w+b") as f:
             f.write(requests.get(mnist_url, stream=True).content)
@@ -25,7 +25,7 @@ def mnist_test(
     x_train, _, x_test, _ = load_mnist()
     x_train = np.divide(x_train, 255)
     x_test = np.divide(x_train, 255)
-    in_len = x_train[0].flatten().shape[0]
+    in_len = x_train[0].shape[0] * x_train[0].shape[0]
     autoencoder = Autoencoder(in_len, bottleneck, 0.001, relu)
     autoencoder.train_dataset(x_train, max_epoch, patience, display_loss=True)
     example: np.ndarray = x_test[np.random.randint(0, len(x_test))]