1、加end=""的运行结果

[Train] epoch: 0, step: 148, loss: 0.84504, accuracy: 0.70
[Train] epoch: 0, step: 294, loss: 0.42226, accuracy: 0.90
[Train] epoch: 0, step: 445, loss: 0.39563, accuracy: 0.85
[Train] epoch: 0, step: 599, loss: 0.37678, accuracy: 0.85
[Train] epoch: 0, step: 751, loss: 0.53066, accuracy: 0.80
[Train] epoch: 0, step: 899, loss: 0.35761, accuracy: 0.80
[Train] epoch: 0, step: 1053, loss: 0.34149, accuracy: 0.85
[Train] epoch: 0, step: 1207, loss: 0.55631, accuracy: 0.85
[Train] epoch: 0, step: 1356, loss: 0.16758, accuracy: 0.90
[Train] epoch: 0, step: 1505, loss: 0.35638, accuracy: 0.90
[Train] epoch: 0, step: 1659, loss: 0.26414, accuracy: 0.90
[Train] epoch: 0, step: 1810, loss: 0.66631, accuracy: 0.75
[Train] epoch: 0, step: 2749, loss: 0.27701, accuracy: 0.90 [Valid] acc: 0.86
[Train] epoch: 1, step: 2749, loss: 0.17052, accuracy: 0.90 [Valid] acc: 0.87
[Train] epoch: 2, step: 2749, loss: 0.14889, accuracy: 0.90 [Valid] acc: 0.88
[Train] epoch: 3, step: 2749, loss: 0.14421, accuracy: 0.95 [Valid] acc: 0.88
[Train] epoch: 4, step: 2749, loss: 0.17614, accuracy: 0.95 [Valid] acc: 0.88
[Train] epoch: 5, step: 2749, loss: 0.11918, accuracy: 0.95 [Valid] acc: 0.89
[Train] epoch: 6, step: 2749, loss: 0.19986, accuracy: 0.95 [Valid] acc: 0.88
[Train] epoch: 7, step: 2749, loss: 0.19529, accuracy: 0.95 [Valid] acc: 0.89
[Train] epoch: 8, step: 2749, loss: 0.14378, accuracy: 0.95 [Valid] acc: 0.88
[Train] epoch: 9, step: 2749, loss: 0.09800, accuracy: 0.95 [Valid] acc: 0.89

2、不加end=""的运行结果

[Train] epoch: 0, step: 0, loss: 2.71104, accuracy: 0.10
[Train] epoch: 0, step: 1, loss: 2.47375, accuracy: 0.25
[Train] epoch: 0, step: 2, loss: 2.33718, accuracy: 0.25
[Train] epoch: 0, step: 3, loss: 2.05763, accuracy: 0.15
[Train] epoch: 0, step: 4, loss: 1.87737, accuracy: 0.25
[Train] epoch: 0, step: 5, loss: 1.76103, accuracy: 0.35
[Train] epoch: 0, step: 6, loss: 1.81363, accuracy: 0.45
[Train] epoch: 0, step: 7, loss: 1.74227, accuracy: 0.35
[Train] epoch: 0, step: 8, loss: 1.16889, accuracy: 0.65
[Train] epoch: 0, step: 9, loss: 1.45857, accuracy: 0.50
[Train] epoch: 0, step: 10, loss: 1.35828, accuracy: 0.60
[Train] epoch: 0, step: 11, loss: 1.24652, accuracy: 0.65
[Train] epoch: 0, step: 12, loss: 1.81420, accuracy: 0.35
[Train] epoch: 0, step: 13, loss: 1.16430, accuracy: 0.60
[Train] epoch: 0, step: 14, loss: 1.15041, accuracy: 0.55
[Train] epoch: 0, step: 15, loss: 0.95684, accuracy: 0.75
[Train] epoch: 0, step: 16, loss: 1.01352, accuracy: 0.65
[Train] epoch: 0, step: 17, loss: 1.00188, accuracy: 0.75
[Train] epoch: 0, step: 18, loss: 1.06917, accuracy: 0.55
[Train] epoch: 0, step: 19, loss: 1.00452, accuracy: 0.65
[Train] epoch: 0, step: 20, loss: 1.32234, accuracy: 0.55
[Train] epoch: 0, step: 21, loss: 0.87749, accuracy: 0.75
[Train] epoch: 0, step: 22, loss: 1.00328, accuracy: 0.65
[Train] epoch: 0, step: 23, loss: 0.85929, accuracy: 0.70
[Train] epoch: 0, step: 24, loss: 0.70125, accuracy: 0.70
[Train] epoch: 0, step: 25, loss: 1.21007, accuracy: 0.55
[Train] epoch: 0, step: 26, loss: 0.74932, accuracy: 0.75
[Train] epoch: 0, step: 27, loss: 1.01770, accuracy: 0.70
[Train] epoch: 0, step: 28, loss: 1.08618, accuracy: 0.45
[Train] epoch: 0, step: 29, loss: 0.81602, accuracy: 0.70
[Train] epoch: 0, step: 30, loss: 0.83498, accuracy: 0.65
[Train] epoch: 0, step: 31, loss: 0.83269, accuracy: 0.70
[Train] epoch: 0, step: 32, loss: 0.68251, accuracy: 0.70
[Train] epoch: 0, step: 33, loss: 1.19818, accuracy: 0.70
[Train] epoch: 0, step: 34, loss: 0.69465, accuracy: 0.80
[Train] epoch: 0, step: 35, loss: 0.61138, accuracy: 0.80
[Train] epoch: 0, step: 36, loss: 0.59016, accuracy: 0.90
[Train] epoch: 0, step: 37, loss: 0.90507, accuracy: 0.65
[Train] epoch: 0, step: 38, loss: 0.78469, accuracy: 0.80
[Train] epoch: 0, step: 39, loss: 0.67537, accuracy: 0.75
[Train] epoch: 0, step: 40, loss: 0.86337, accuracy: 0.65
[Train] epoch: 0, step: 41, loss: 0.78989, accuracy: 0.60
[Train] epoch: 0, step: 42, loss: 0.46639, accuracy: 0.90
[Train] epoch: 0, step: 43, loss: 0.72662, accuracy: 0.65
[Train] epoch: 0, step: 44, loss: 0.47574, accuracy: 0.85
[Train] epoch: 0, step: 45, loss: 0.81599, accuracy: 0.65
[Train] epoch: 0, step: 46, loss: 1.08804, accuracy: 0.55
[Train] epoch: 0, step: 47, loss: 0.87437, accuracy: 0.70
[Train] epoch: 0, step: 48, loss: 0.85379, accuracy: 0.70
[Train] epoch: 0, step: 49, loss: 0.84142, accuracy: 0.70
[Train] epoch: 0, step: 50, loss: 0.68575, accuracy: 0.70
[Train] epoch: 0, step: 51, loss: 0.54696, accuracy: 0.85

老师，您在课上运行的结果（加end=" "）显示没有把每一个展开，我运行的时候，一半展开一般不展开，可我看代码又感觉应该都展开，这里不太明白。