new Cross

Code/train.py

@@ -105,7 +105,8 @@ def train(model, name, seed,gradient_accumulation_steps,mixup, threshold, lambda
 						
 					print("logits: ", logits) #print("logits: ", logits.size())
 					print("labels size: ", new_labels_batch.size())
-					loss_fct = CrossEntropyLoss()
+
+					loss_fct = SoftCrossEntropyLoss()
 
 					loss_2=loss_fct(logits.view(-1, 2).to("cuda"), new_labels_batch.view(-1).to("cuda"))
 					print("MixUp Loss: ", loss_2)
@@ -122,7 +123,7 @@ def train(model, name, seed,gradient_accumulation_steps,mixup, threshold, lambda
 			#print(outputs[0].size())
 			#progress_bar.update(1)
 		#print("one epoch done")
-
+	
 	#print(model_name)
 	evaluation_test = evaluation.evaluate_model(model, name,  test_dataset, learning_rate, test_batch_size)
 	evaluation_train = evaluation.evaluate_model(model, name, train_dataset, learning_rate, test_batch_size)
@@ -132,7 +133,9 @@ def train(model, name, seed,gradient_accumulation_steps,mixup, threshold, lambda
 
 	return evaluation_test, evaluation_train
 
-
+def SoftCrossEntropyLoss (input, target):
+    logprobs = torch.nn.functional.log_softmax (input, dim = 1)
+    return  -(target * logprobs).sum() / input.shape[0]
 	
 def mixup_function(batch_of_matrices, batch_of_labels, l, t):
 	runs = math.floor(batch_of_matrices.size()[0]/2)