autograder 28

Assignment2/main.py

@@ -14,7 +14,7 @@ def taskXor():
 	# raise NotImplementedError
 	###############################################
 	YTrain , YVal, YTest = np.array([int(i[1]==1) for i in YTrain]).reshape((-1,1)),  np.array([int(i[1]==1) for i in YVal]).reshape((-1,1)),  np.array([int(i[1]==1) for i in YTest]).reshape((-1,1))
-	lr,batchSize,epochs = 0.2,50,10
+	lr,batchSize,epochs = 0.01,50,10
 	nn1 = nn.NeuralNetwork(lr, batchSize, epochs)
 	# Add layers to neural network corresponding to inputs and outputs of given data
 	input_layer = XTrain.shape[1]
@@ -48,7 +48,7 @@ def preprocessMnist(X):
 def taskMnist():
 	XTrain, YTrain, XVal, YVal, XTest, _ = loadMnist()
 	# Create a NeuralNetwork object 'nn1' as follows with optimal parameters. For parameter definition, refer to py file.
-	lr,batchSize,epochs = 0.2,256,50
+	lr,batchSize,epochs = 0.01,256,50
 	nn1 = nn.NeuralNetwork(lr, batchSize, epochs)
 	# Add layers to neural network corresponding to inputs and outputs of given data
 	input_layer = XTrain.shape[1]

Assignment2/nn.py

@@ -131,7 +131,7 @@ class FullyConnectedLayer:
 		# TASK 1a (Marks 0) - YOUR CODE HERE
 		# raise NotImplementedError
 		self.weights = np.random.randn(in_nodes,out_nodes)/np.sqrt(in_nodes)
-		self.biases = np.zeros((out_nodes,1))
+		self.biases = np.zeros(out_nodes)
 		###############################################
 		# NOTE: You must NOT change the above code but you can add extra variables if necessary
 		
@@ -207,12 +207,12 @@ class FullyConnectedLayer:
 		###############################################
 		# TASK 1d (Marks 4) - YOUR CODE HERE
 		if self.activation == 'relu':
-			self.data = X @ self.weights + self.biases.T
-			return self.relu_of_X(self.data)
+			self.data = self.relu_of_X(np.add(X @ self.weights , self.biases))
+			return self.data
 			raise NotImplementedError
 		elif self.activation == 'softmax':
-			self.data = X @ self.weights + self.biases.T
-			return self.softmax_of_X(self.data)
+			self.data = self.softmax_of_X(np.add(X @ self.weights , self.biases))
+			return self.data
 			raise NotImplementedError
 		else:
 			print("ERROR: Incorrect activation specified: " + self.activation)
@@ -239,7 +239,7 @@ class FullyConnectedLayer:
 			print("ERROR: Incorrect activation specified: " + self.activation)
 			exit()
 		self.weightsGrad = (activation_prev.T @ inp_delta)/delta.shape[0]
-		self.biasesGrad = np.average(inp_delta,axis=0).reshape((delta.shape[1],-1))
+		self.biasesGrad = np.average(inp_delta,axis=0)
 		new_delta = inp_delta @ self.weights.T
 		return new_delta
 		###############################################