Tian14267

AttributeError: Not implemented

4

**I covert my onnx model,and get this problem:** ............ ............ DEBUG:onnx2keras:... DEBUG:onnx2keras:Check if all inputs are available: DEBUG:onnx2keras:Check input 0 (name 565). DEBUG:onnx2keras:Check input 1 (name 567). DEBUG:onnx2keras:Check input 2...

all the input arrays must have same number of dimensions, but the array at index 0 has 1 dimension(s) and the array at index 1 has 0 dimension(s)

4

**Describe the bug** **I get this error:** Traceback (most recent call last): File "torch2keras.py", line 83, in transforms_2() File "torch2keras.py", line 76, in transforms_2 k_model = pytorch_to_keras(model.module, input_var, (3, 448,...

作者你好，我在运行“a1_seq2seq_attention_train.py”的时候，设置"multi_label_flag=False"，却遇到错误提醒：“You must feed a value for placeholder tensor 'decoder_input' with dtype int32 and shape [?,6]” 在你代码 103 、104行说明，使用FLAGS.multi_label_flag=Flase的时候，不需要 decoder_input 才对。  请问这是什么情况？

你好，我想请问下，怎么进行GPU训练? 我设置了“os.environ["CUDA_VISIBLE_DEVICES"] = "0" ”，但是代码还是在CPU上面运行。请问如何设置GPU运行？

Hello! Thank you so much for publishing such a great code! Thanks to you, I'm enjoying my voice conversion! Here I have a question about how to set the config...

服务多并发出现多个并发的结果相互串了的情况

2

算法：fastspeech2, pwgan 服务部署：websocket 并发：2个并发 具体情况：并发1的文本，出来的语音确是并发2的结果；并发2的文本，出来的语音确是并发1的结果；即，两个结果搞串了。 情况追踪： 通过追踪发现，模型的输入是正常，但是输出不正常。  `phones_handle`的输入正常，`am_output_data`的结果却不对。请问这情况是什么原因啊，这么解决这个问题。

[BUG] FileNotFoundError: [Errno 2] No such file or directory: '/root/Documents/MFA/chunjiao_0310/corpus_data/split1/feats.pinyin-lexicon-r.0.scp'

2

**Debugging checklist** **Describe the issue** system: **docker** -- ubuntu version: **Montreal-Forced-Aligner 2.0.0b7** operate: mfa train .... Bug detail: ``` WARNING - WARNING: Using old temp directory, this might not be...

Error Code 4: Internal Error (Network must have at least one output)

9

## Description I get this error when covert onnx to TRT : ``` Loading ONNX file from path /data/vocoder_24k_3.onnx... Beginning ONNX file parsing [05/19/2022-19:11:54] [TRT] [W] onnx2trt_utils.cpp:365: Your ONNX model...

RuntimeError: Resize coordinate_transformation_mode=pytorch_half_pixel is not supported in Tensorflow.

2

onnx转pb模型的时候，报这个错误： Traceback (most recent call last): File "onnx2pb.py", line 45, in onnx2pb_2(onnx_input_path) File "onnx2pb.py", line 14, in onnx2pb_2 tf_rep = prepare(model) File "/home/fffan/下载/onnx-tensorflow-rel-1.6.0/onnx_tf/backend.py", line 66, in prepare return cls.onnx_model_to_tensorflow_rep(model, strict)...

Do you have chinese-data model?