Check Lamda value

Code/train.py

@@ -112,7 +112,7 @@ def train(model, name, seed,gradient_accumulation_steps,mixup, threshold, lambda
 					print("logits: ", logits)
 					target = new_labels_batch.view(-1).to("cuda")
 					print("Newlabels: ", new_labels_batch)
-					loss_2 = cross_entropy(logits, target)
+					loss_2 = cross_entropy(logits, target, lambda_value)
 					#loss_2 = SoftCrossEntropyLoss(logits.view(-1, 2).to("cuda"), new_labels_batch.view(-1).to("cuda"))
 					#loss_2 = torch.nn.functional.cross_entropy(preds, target.long())
 					print("MixUp Loss: ", loss_2)
@@ -142,7 +142,7 @@ def train(model, name, seed,gradient_accumulation_steps,mixup, threshold, lambda
 #log base e
 #Fkt vom Meeting
 def cross_entropy(logits, target, l):
-	print("Lambda:", l)
+	print("Lamda Value:", l)
 	#makes the logits in log (base) probabilities
 	logprobs = torch.nn.functional.log_softmax(logits, dim=1)
 	value = target.item() #gets Item (0. or 1.)
@@ -154,21 +154,6 @@ def cross_entropy(logits, target, l):
 	else:
 		print("Mixed Case")
 
-#kann weg
-# def cross_entropy(logits, target):
-#     log_q = torch.log_softmax(logits, dim=1)
-#     return -torch.sum(log_q[range(log_q.shape[0]), target])
-
-# def cross_entropy(logits, target):
-#     # Calculate log_q
-#     log_q = torch.log_softmax(logits, dim=1)
-# 	#define classes/options
-#     target_class = (target == 0).float()
-#     target_class2 = (target == 1).float()
-#     target = target.float()
-# 	# calculate sum of losses of batch size
-#     return -(target_class * log_q[:, 0] + target_class2 * log_q[:, 1] + (1 - target_class - target_class2) * (target * log_q[:, 1] + (1 - target) * log_q[:, 0]))
-
 
 def mixup_function(batch_of_matrices, batch_of_labels, l, t):
 	runs = math.floor(batch_of_matrices.size()[0]/2)