beinabih / pytorch-headtrip Goto Github PK

Great work.

Are the models the systems used the original caffe style models used in the original deep dream caffe implementation or some other format. ( I have other caffe models and was hoping I can use them with your code.)

Does this install work in windows10/11? Again the reginal deep dream / caffe implementation is harder to get running on modern cuda windows10 anymore.

thanks

Hello I am a newbie and I'm using this code to render visuals for integration in a movie sequence. I'm new to coding or python, not experienced at all really, and I got this error:

RuntimeError: CUDA out of memory. Tried to allocate 188.00 MiB (GPU 0; 6.00 GiB total capacity; 4.29 GiB already allocated; 0 bytes free; 4.74 GiB reserved in total by PyTorch)

I was wondering if you know what I could do to fix this problem besides getting a new graphics card or using a different computer.

Awesome repo.
I also made a colab notebook for this. (You can ad this to readme if you want)

I encountered several errors when I set no_class: True

`Traceback (most recent call last):
  File "dream.py", line 470, in <module>
    start_dreamer(config)
  File "dream.py", line 451, in start_dreamer
    dreamer = Dreamer(img_p, outpath, config)
  File "dream.py", line 74, in __init__
    self.model = nn.Sequential(*self.layers[: (self.at_layer_para + 1)])
AttributeError: 'Dreamer' object has no attribute 'layers'`

And It is using the cached MiDAS data. Can you tell me how to use this depth function properly?

`Using cache found in depth_model/intel-isl_MiDaS_master
Loading weights:  None
Using cache found in depth_model/rwightman_gen-efficientnet-pytorch_master
Using cache found in depth_model/intel-isl_MiDaS_master`

This is what I made using the colab with model: masnet and iterations: 10