softmac

Code/train.py

@@ -137,23 +137,17 @@ def train(model, name, seed,gradient_accumulation_steps,mixup, threshold, lambda
 
 	return evaluation_test, evaluation_train
 
-#works, but little weird output...
-# def cross_entropy(logits, target):
-#     log_softmax = torch.nn.functional.log_softmax(logits, dim=1)
-#     loss = -torch.sum(target * log_softmax, dim=1).mean()
-#     return loss
-
 #pytorch Forum, try with dim=1 for targets
-# def cross_entropy(logits, target):
-# 	print("Cross Entropy Target: ", target)
-# 	logprobs = torch.nn.functional.log_softmax (logits, dim = 1)
-# 	return  -torch.mean(torch.sum(target * logprobs, dim=1))
+def cross_entropy(logits, target):
+	print("Cross Entropy Target: ", target)
+	logprobs = torch.nn.functional.log_softmax (logits, dim = 1)
+	return  -torch.mean(torch.sum(target * logprobs, dim=1))
 
 #without softmax
-def cross_entropy(logits, target):
-    log_probs = -torch.log(torch.exp(logits) / torch.sum(torch.exp(logits), dim=1, keepdim=True))
-    loss = -torch.mean(torch.sum(target * log_probs, dim=1))
-    return loss
+# def cross_entropy(logits, target):
+#     log_probs = -torch.log(torch.exp(logits) / torch.sum(torch.exp(logits), dim=1, keepdim=True))
+#     loss = -torch.mean(torch.sum(target * log_probs, dim=1))
+#     return loss
 
 def mixup_function(batch_of_matrices, batch_of_labels, l, t):
 	runs = math.floor(batch_of_matrices.size()[0]/2)