Kongsea

Thank you. It said the input images need to be squared, however, my images are not. How to process it or modify the code?

Thank you. I will try it too.

Have you achieved it? @xymeng16

Look forward to it.

Train using cpu? Are you kidding me?

I want to know how to switch vgg model to resnet. Obviously, resnet will be better.

我训练的时候，运行到测试这一步，直接出错： > File "run.py", line 32, in main > FLAGS.aligning, FLAGS.eval_step_interval, FLAGS.output_dir) > File "tensorflow-examples/speech/steps/train.py", line 87, in train > dense_labels = sparse_tuple_to_string(test_data[1], lexicon) > NameError: name 'test_data' is not...

@kevinan1 麻烦看一下呢？谢谢。

而且这里的这个lexicon也是未定义吧。

@GangTimes 我也是这么改的，也是输出了拼音。 有后续进展，记得分享一下哦。