TensorFlow2.0-Examples
TensorFlow2.0-Examples copied to clipboard
YoloV3 saving weights
You can use tf.layers.Lambda to include all of your non-layer functions in the YOLO network(like tile,cast,etc.), thus they are technically a layer but not functions in the network, and you can write and load weights.h5 files. However, I still don't know how to save the whole network.
Me too,good question!When I run train.py to train yolo network,once epoch finished,it raise error like:
Traceback (most recent call last):
File "train.py", line 95, in
Mee too i do not know how to save .h5 who can tell me
Mee too i do not know how to save .h5 who can tell me
can you save as xxx.weights file?,i got many files like this xx.data-00001-of-00002 xx.index xx.chechpoint
Mee too i do not know how to save .h5 who can tell me
you can use model.save(xxxxx.5h)