Ali Mohammad
Ali Mohammad
did you manage to solve this ?
I found the problem to be with loading the facenet model, did you find a workaround? error message ` ValueError: Node 'gradients/InceptionResnetV1/Bottleneck/BatchNorm/cond/FusedBatchNorm_1_grad/FusedBatchNormGrad' has an _output_shapes attribute inconsistent with the GraphDef...
update: you can simply run the code for inference on tf2 using ` import tensorflow.compat.v1 as tf tf.disable_v2_behavior() ` and the frozen model provided.
@github2016-yuan just use the frozen model pb, if you don't have it then I didn't find a work around
I found that pretrained model can't be loaded using tf2, did you manage to work with it ?
you can find good tutorial [here](https://www.tensorflow.org/lite/convert) since you have the ckpt file, it should be easy to do, however it comes with some limitations, for example i didn't find a...
you can check data.py to see how the code handles bbox in different cases
Hi, can you guys help me with steps to train deeplab on a custom dataset using tf2, just the basic outline, I'm still a beginner and I don't know where...
does this affect the segment start/end as well? so if a segment is "2014 something" then the starting point would be at "something" or at "2014"
changing the order did fix the issue for me