Connor Eaton
Connor Eaton
I am trying to implement this [paper](https://www.mdpi.com/2076-3417/10/11/4002), which uses LipNet to create a 96d feature vector as features for training another model. Has anyone tried this? I want to pass...
I keep running into tons of errors around versioning. This code did not work with the latest versions of torch, fastai, and transformers. I downgraded to: ``` !pip install fastai==2.1.2...
When I run the suggested command, I get this error: ``` $ pip3 install mtcnn Collecting mtcnn Downloading https://files.pythonhosted.org/packages/67/43/abee91792797c609c1bf30f1112117f7a87a713ebaa6ec5201d5555a73ef/mtcnn-0.1.0-py3-none-any.whl (2.3MB) 100% |████████████████████████████████| 2.3MB 604kB/s Collecting opencv-python>=4.1.0 (from mtcnn) Using cached...
Thanks for providing your great code. I have ran the wav2vec emotion classification of greek audio and it works great. However, I keep running into memory errors when changing the...
When plotting the output from your program, it produces a waveform like this: I understand this output is more sensitive than an on-finger bpm reader, but with a little imagination...
Hello, I am looking to deploy a tsai trained model for inference. I see you created the tsai.inference module for lightweight inference with load_learner. This looks like it will be...
Thank you for your fastai/huggingface nlp classification blog. It was very cool. Do you know how to run learn.export()? I am trying to save the trained model. I get this...
I could be wrong, but it looks like the watershed algorithm is not implemented properly. There is no output variable declared and used. How were you intending on using the...
Hello, thanks for working on this. I am trying to convert text and image models I trained with the current fastiai (2.7.11) to onnx and this library seems like what...
Hello, thank you for providing your code. I read your response to the previous issue regarding the missing swda_data file but I do not understand how to preprocess the data...