tensorflow-wavenet icon indicating copy to clipboard operation
tensorflow-wavenet copied to clipboard

generate problem

Open zsxgb opened this issue 7 years ago • 1 comments

I have a mistake, it seems a bit troublesome I use Python train.py --data_dir=corpus --gc_channels=32 Train

I use Python generate.py --samples 16000 logdir/train/2017-02-xxxxx-xx-xx/model.ckpt-xxx Generate There is no problem with this

When I use Python generate.py --samples 16000 --wav_out_path speaker311.wav --gc_channels=32 --gc_cardinality=377 --gc_id=311 logdir/train/2017-xx-xxxxx-xx-xx/model.ckpt-xxx When generating.There will be an error.Finally

NotFoundError (see above for traceback): Key wavenet/dilated_stack/layer22/gc_gate not found in checkpoint [[Node: save/RestoreV2_159 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/RestoreV2_159/tensor_names, save/ RestoreV2_159/shape_and_slices)]]

I looked at some of the issure, as if it did not solve the problem. What should I do

zsxgb avatar Apr 23 '18 03:04 zsxgb

do you have this ckpt files?

Yaque avatar Aug 04 '18 01:08 Yaque