TomRiddle

@MariaAlpaki if you use python3.6 you can install tensorflow==1.0.0 I have also the same issue solved it by using 3.6

I have same problem like but I have anaconda3 create env in that env installed all the requirements Remember to use python 3.6 env if higher you can't install tensorflow...

@danraymond do you have python3.6 installed you can verify it by typing python -V in terminal its

Yes, You need to use a different algorithm called [FaceRecognition](https://github.com/ageitgey/face_recognition). Use luminoth for person extraction and the run [FaceRecognition](https://github.com/ageitgey/face_recognition) on that extracted person and please Close this it is not...

when i debug found on [line](https://github.com/mit-han-lab/temporal-shift-module/blob/4759ad8da09fcd5dd00fe243ca046669f0e0576a/online_demo/main.py#L60) is taking time any idea nearly 5 to 10 min

@zedmanish Hi as @AIZOOTech said "Hi, this model is a simple SSD framework. Training process is quite easy. You can find many open source SSD implementation on Github. The model360...

@MyraBaba how did you solve `RuntimeError: Parameter 'conv2d_0bias' was not initialized on context cpu(0). It was only initialized on [gpu(0)]. ` error

@MyraBaba any update sorry to bother you. How did you add extra default ctx to gpu.

this is a simple SSD model just google it you will find. I am planning to create the training code for this but its better if @AIZOOTech provides his code...

@1996scarlet and @MyraBaba did you solve this error? Because I am also getting this error ```[0] Exception in thread Thread-2: Traceback (most recent call last): File "/media/mustafa/ubuntu_backup/anaconda3/lib/python3.7/threading.py", line 917, in...