-
代码使用train.py中的代码，但是数据集是自己的，训练完成了，但是infer时报错：
EnforceNotMet: Invoke operator sequence_expand error.
C++ Callstacks:
DataType of Paddle Op sequence_expand Y must be the same. Get (float) != (int64_…
-
Hi all,
I am trying to do sequence tagging (i.e., a label for each token in a sequence) using the `BiSequencer` model with LSTMs and have been running into some trouble trying to determine how to form…
-
Hey, doing the basic step, to LSTM model.
``
# Returns a compiled model identical to the previous one
onnx_model = onnx.load("stock_price.onnx")
k_model_onnx = onnx_to_keras(onnx_model, 'lstm_inp…
-
Django 1.7's migrations should be supported.
Is this something that is being worked on or has been attempted? I am interested in helping out with this if you think it would be a reasonable addition. …
AMeng updated
9 years ago
-
rzai@rzai00:~/prj/LSTM-ER/build$ make -j8
[ 3%] [ 6%] [ 10%] Building CXX object cnn/cnn/CMakeFiles/cnn.dir/cnn.cc.o
[ 13%] [ 16%] Building CXX object cnn/cnn/CMakeFiles/cnn.dir/conv.cc.o
Buildin…
-
### What happened + What you expected to happen
I had a RNN model inheriting modelV2 that had worked well with ray 2.2.
In ray 2.9, I set the option as required:
config.experimental(_enable_ne…
-
## Describe the question
In Diarization task, i train on AMI train-dev set and ICSI corpus , i test on AMI test set. Both datasets include audios of 3-5 speakers in 50-70 minutes. My d embedding tra…
-
@cynthia in [his talk](https://www.w3.org/2020/06/machine-learning-workshop/talks/machine_learning_in_web_architecture.html?) points out the lack of consensus on a particular format for ML models:
> …
-
Sorry for the somewhat unscoped question, but I'm really not sure how to troubleshoot this.
I was using PlaidML to accelerate some experimentation I'm doing for a course. I successfully trained a n…
-
Dear @taolei87 ,
As part of my thesis project I have replicated your work in question retrieval using Tensorflow.
In your code you provide the loss for the training, as well as the performance fo…