Drew McGowen
Drew McGowen
I'm also running into this issue with GoldSrc Package 2.3, but only with the Steam version. Does it have anything to do with the fact that the Steam version of...
I should also note that I did not test with CPU-trained model because it runs significantly slower (about 2 seconds per 100 iterations on GPU vs 90 seconds on CPU).
Update: the issue is due to type-mismatches. CUDA tensors use `float` by default, whereas the normal torch tensor uses `double`. I hacked together a little python script to convert the...
I've uploaded the scripts at https://github.com/quantumdude836/sound-rnn-fixup
After further investigation, the rates actually max out at whatever rate a single factory building consumes. For example, the recipe for FICSMAS Tree Branches consumes 10 gifts per minute; in...
Did some experimenting/debugging... Looks like I still had some stale preferences (in %APPDATA%) from an older build that had the builtin fonts pointing to a different directory. After I removed...