Is this normal?

[cayman1021]

When train.py is running, I always see it reads the same first 50 photos (which also means containing the same plates). Then I found something in train.py, line 232: test_xs, test_ys = unzip(list(read_data("test/*.png"))[:50]) Does that mean it always get the first 50 elements from "test" folder? Is this normal?

[fkoorc]

test_xs, test_ys = unzip(list(read_data("test/*.png"))[:batch_size])

[fkoorc]

def batch function and make sure you change the related paramater

[ZengyuanYu]

I also meet this erro and my train loss down on 300+ but acc under 50! however, 50 jpg always train I don't work it

like this: 苏AZ3A25 1.0 <-> 苏AZ3A25 1.0 苏AJ3H16 1.0 <-> 苏AJ3H16 1.0 苏AC0378 1.0 <-> 苏AS0377 1.0 苏AY9L95 1.0 <-> 苏AX9L15 1.0 苏AZ1W57 1.0 <-> 苏AZ7X17 1.0 苏AR3595 1.0 <-> 苏AR0195 1.0 苏AI0P50 1.0 <-> 苏AI0P59 1.0 苏AE8J34 1.0 <-> 苏AE8J34 1.0 苏AO9R64 1.0 <-> 苏AO9R64 1.0 苏AC5N78 1.0 <-> 苏AC5N78 1.0 苏AU4A12 1.0 <-> 苏AU4A12 1.0 苏AN4780 1.0 <-> 苏AN4780 1.0 B77120 42.00% 100.00% loss: 552.0714111328125 (digits: 552.0714111328125, presence: 1.8921246439497583e-15) |XX X X XXXX XX XXXX XX XXX XX XXX XXXXX | time for 60 batches 9.751856088638306

[chl916185]

@ZengyuanYu 这个代码没有用lstm吧

[Abduoit]

@cayman1021 @fkoorc could you please tell What are the related parameters we should change, including the following line test_xs, test_ys = unzip(list(read_data("test/*.png"))[:50])