bhack
bhack
I don't know if you could be interested in https://llvm.discourse.group/t/numpy-scipy-op-set/
/cc @speedinghzl
I've tried hpe with your last hourglass_bn_100 but seems that doesn't work. I've used on or two image from the dataset.
Is there not too much duplicated/overlapping code now between hourglass_tiny and hourglass_tiny_testing?
Yes I'have seen this.. but was just a feedback about how the code was organized between this two files.
There are missing Yolo python imports.. Another alternative is to use one of the models zoo available in TF new [Object detection API](https://github.com/tensorflow/models/blob/master/object_detection/)
Now yolo code is imported in the repository but you are mixing your code under MIT with unkown yolo code license. [This version](https://github.com/hizhangp/yolo_tensorflow) is under the same of your code...
AdamaW Is now in Keras if you want to add something to the doc you need to do It there: https://github.com/keras-team/keras/blob/master/keras/optimizers/optimizer_experimental/adamw.py
Can you try to submit a PR?
@seanpmorgan Do we still needs these build_deps with the new 2.9 toolchain?