Open kylemcdonald opened 6 years ago
I'll investigate. What do True
and False
means (Where are they from)?
Those are the labels of the input image. In this case, I'm predicted 73 attributes from the LFWA+ dataset. "True" means "smiling" and "False" means "not smiling". I provided example images.
Thanks. I'll investigate more.
Could you share more information (model h5 file, train script, etc.) with me if possible?
Here is an h5 file and the notebook I used for training, and export. Sorry it's so messy!
https://www.dropbox.com/s/tdv8jgor4gl9jnm/checkpoint-2.42-04.h5?dl=0 https://www.dropbox.com/s/ggt68cod8qzu1pp/SEResNet-train%2Bexport.zip?dl=0
Sorry but the h5 file you shared may be the other model. its output shape is (batch_size, 20)
.
Sorry, it's my fault! Here is the correct .h5 file:
https://www.dropbox.com/s/lm7k336mt6vqfhz/checkpoint-0.29-04.h5?dl=0
The other one uses the same input data, but has a softmax output across a different distribution.
I’m still trying to get this to work, but I feel like I must have made some simple mistake... :(
I exported a 73-label multilabel network. It was made with Keras using sigmoid outputs. I get very different outputs from each backend, and they are all wrong.
I'm using the SEResNet architecture.
I'm setting up the runner with:
Here's the entire exported backend and test code if it's helpful: https://www.dropbox.com/s/wf830x6ah7rp6bx/lfwa%2B.zip?dl=0
Here's the
model.summary()
: