Optimzed stuff

rgbAI/lib/ailib/ai.py

@@ -1,5 +1,6 @@
 import numpy as np
 from copy import deepcopy as copy
+import os
 
 def sigmoid(x):
 	return 1/(1 + np.exp(-x))
@@ -137,7 +138,7 @@ def mutateProps( inpObj, curCost:float, maxLayer:int, gradient:list ):
 
 	for layer in range(maxLayer):
 		lr = getLearningRate( curCost, gradient[layer], maxLayer )
-		print(lr)
+		# print(lr)
 
 		obj.weights[layer] -= lr["weight"] * gradient[layer]["weight"] # mutate the weights
 		obj.bias[layer] -= lr["bias"] * gradient[layer]["bias"]
@@ -162,6 +163,7 @@ def learn( inputNum:int, targetCost:float, obj, theta:float, curCost: float=None
 		grads, costW, costB, curCost = gradient( inp, obj, theta, maxLen - 1 )
 
 		obj = mutateProps( obj, curCost, maxLen, grads ) # mutate the props for next round
+		os.system("clear")
 		print(f"Cost: {curCost}")
 
 

rgbAI/main.py

@@ -7,11 +7,11 @@ class rgb(object):
 
 		if( not loadedWeights or not loadedBias ): # if one is null (None) then just generate new ones
 			print("Generating weights and biases...")
-			self.weights = [ ai.genRandomMatrix(3, 8), ai.genRandomMatrix(8, 8), ai.genRandomMatrix(8, 3) ] # array of matrices of weights
+			self.weights = [ ai.genRandomMatrix(3, 8), ai.genRandomMatrix(8, 8), ai.genRandomMatrix(8, 8), ai.genRandomMatrix(8, 3) ] # array of matrices of weights
 			# 3 input neurons -> 8 hidden neurons -> 8 hidden neurons -> 3 output neurons
 
 			# Generate the biases
-			self.bias = [ ai.genRandomMatrix(1, 8), ai.genRandomMatrix(1, 8), ai.genRandomMatrix(1, 3) ]
+			self.bias = [ ai.genRandomMatrix(1, 8), ai.genRandomMatrix(1, 8), ai.genRandomMatrix(1, 8), ai.genRandomMatrix(1, 3) ]
 			# This doesn't look very good, but it works so...
 
 			self.learningrate = 0.01 # the learning rate of this ai
@@ -29,7 +29,7 @@ class rgb(object):
 		return cost
 
 	def learn( self ):
-		ai.learn( 3, 0.0001, self, 0.001 )
+		ai.learn( 3, 0.0001, self, 0.000001 )
 
 	def think( self, inp:np.array ):
 		print("\n-Input-")