livyer

> 100步左右就可以了，主要跑完了，不能单独输入图片去测试 感觉６０多次后就收敛的比较好了.

> 你们运行的test的时候，不会报tensorflow.python.framework.errors_impl.InvalidArgumentError: Assign requires shapes of both tensors to match. lhs shape= [512,2667] rhs shape= [512,1788] > [[Node: save/Assign_41 = Assign[T=DT_FLOAT, _class=["loc:@H6"], use_locking=true, validate_shape=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"](h6/Adam_1, save/RestoreV2:41)]] > 这种错误吗？ 就是报这个错.　还没找到办法解决,　

> Assign requires shapes of both tensors to match. lhs shape= [512,14] rhs shape= [512,1788] > [[node save/Assign_41 (defined at /home/junli/Downloads/speech_recognition-master/model.py:186) = Assign[T=DT_FLOAT, _class=["loc:@H6"], use_locking=true, validate_shape=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"](h6/Adam_1, save/RestoreV2:41)]] 我也是直接用test.py训练Ｄ*字头的测试集报这个错,　感觉这个:hs...