Golbstein / Keras-segmentation-deeplab-v3.1

An awesome semantic segmentation model that runs in real time
175 stars 73 forks source link

Code Debugging #17

Open zengzhi2015 opened 5 years ago

zengzhi2015 commented 5 years ago

Thanks for your great efforts so that I can use your code to build a new structure upon DeepLabv3p easily. But I do find a few bugs inside your code. I found them by debugging line by line. In my own project, I corrected these bugs but also reshaped a bit the structure of the code, like defining more functions for readability and modifying certain functions. However, I am not sure if it is proper to commit my modifications, since the modifications may violate the interface of your own project. Would you like to give me a little advice? Thanks! By the way, I will finish the whole debugging in several weeks.

ankitksharma commented 4 years ago

Hi @zengzhi2015

I myself have been struggling to correct all the bugs in the code. I'm still stuck with Index out of range using input dim 3; input has only 3 dims for 'loss/pred_mask_loss/strided_slice_1' Not sure what's the issue.

Would you be able to share your working version?

curryJ commented 3 years ago

Could you tell me your keras version and tf version? There are some bugs when I use tf 2.0 and keras 2.2.4.I want to solve this Incompatible problem.Thank a lot!

ckolluru commented 3 years ago

I've been able to compile the model with tensorflow v1.11.0 and keras v2.2.4

Using tensorflow v1.14.0 failed, creating the model resulted in a TypeError. Maybe try keras v2.3.1 when using tf v2.0? There are some compatibility issues:

https://stackoverflow.com/questions/62690377/tensorflow-compatibility-with-keras