Ianmcmill

Yes you are right. I realized that the servo had a hard time holding the pen in the raised position.

So if 16 is set in the sketch my motors do 3200 steps. I don't have to set 3200 explicitly. The rotation movement is very smooth if I recall now....

I get this error on Windows too. I am a total noob in programming but had a basic python introduction. Might this be because of linux/windows paths? I thought os.path...

Have copy and pasted everything as in the read me. No errors. Nvidia-smi shows that the python3 process is using 69mb but the volatile GPU usage is 1-4% Ubuntu 16.04....

I just found this on githubgist: https://gist.github.com/ageitgey/629d75c1baac34dfa5ca2a1928a7aeaf > These instructions assume you don't have an nVidia GPU and don't have Cuda and cuDNN installed and don't want GPU acceleration (since...

I think I closed this to early because I still think it does not utilize CUDA. Just for clarification. When I run the script and check GPU load with nvidia-smi...

I would suggest running this in a virtualenv. Saves you a lot of headaches. There are tutorials how to install virtualenv for Windows. You can then create virtual environments with...

What does `--pre_trained_model False` mean? When I want to resume training with `--checkpoint ./experiment_SRResnet/` and `--pre_trained_model False` I get the error: > ValueError: The passed save_path is not a valid...

Would decreasing the batch size to say 4 during training also decrease "quality" of resulting images? Or would just take longer but give the same output as a batch size...

I would like to be able to read the retweet queue. Just for the verbose-addicted users here. The --l FILENAME is rather simple a output log. Maybe more verbose details...