Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Problems with usage in DeepDream #73

Open
ad48hp opened this issue Feb 13, 2020 · 10 comments
Open

Problems with usage in DeepDream #73

ad48hp opened this issue Feb 13, 2020 · 10 comments

Comments

@ad48hp
Copy link

ad48hp commented Feb 13, 2020

I tried to use the model in the consistently zooming-up script, and while the original MIT Places seemed to work quite well, the one on this didn't yet..

Does anyone have some suggestive ideas ?

@ProGamerGov
Copy link

It's the layer, channels, and input that are affecting it, I think. Changing any of those should help.

@ProGamerGov
Copy link

ProGamerGov commented Feb 19, 2020

I've got Places205 working with DeepDream in PyTorch, so I'll see if Places365 works just as well once I convert it.

@ProGamerGov
Copy link

@ad48hp

Here's a random Places205 layer:
inception4c_out

And a random Places365 layer:

inception4c_out

It seems to work just as well for me.

@ad48hp
Copy link
Author

ad48hp commented Feb 23, 2020

Can you try the videoify.py script and post the results ?

Try with the StepSize settled to 1.5 and then -1.5..

@ProGamerGov
Copy link

@ad48hp I don't have a working Caffe setup for running the script.

You can try running my WIP project here, with the following parameters:

python3 neural_dream.py -backend cudnn -octave_scale 0.25 -num_octaves 4 -octave_mode advanced -octave_iter 10 -tv_weight 0 -print_octave_iter 5 -loss_mode l2 -seed 876 -model_file models/googlenet_places365.pth -init image -dream_layers inception_4c_pool_proj -content_image test_image.png -learning_rate 5 -image_size 1140 -num_iterations 10 -zoom 95

@ad48hp
Copy link
Author

ad48hp commented Feb 28, 2020

Code seems to be bugged..

img.data = adjust_contrast(img, r=clamp_val, params.adjust_contrast)
The r parameter is unnecessary, and throws me an error "positional argument follows keyword argument"

ModuleNotFoundError: No module named 'dream (in dream_model.py)'

@ProGamerGov
Copy link

@ad48hp If you change the neural_dream.py script to dream.py, then it should work I think.

@ad48hp
Copy link
Author

ad48hp commented Feb 28, 2020

That breaks the statements..
from neural_dream.CaffeLoader import loadCaffemodel, ModelParallel, Flatten import neural_dream.dream_utils as dream_utils import neural_dream.dream_model as dream_model from neural_dream.dream_auto import auto_model_mode, auto_mean from neural_dream.dream_experimental import ChannelMod

Do you try to run the code before uploading to Github ?
Sometimes some code worked on my computer well, and others marked it sorta as broken..

Also, there are more bugs, like AttributeError: module 'neural_dream' has no attribute 'DreamLossHook', which is why i recommend trying the code (i run it with P3.6)

@ProGamerGov
Copy link

ProGamerGov commented Feb 28, 2020

@ad48hp Put all the files in a folder/directory called neural_dream except for dream.py. I haven't worked a ton with multiple files like this before, so I'm still learning how things work. The import statements will import the file from the neural_dream folder.

I also just successfully ran the code on PC, so it doesn't seem like there are any bugs stopping it from working right now.

@ProGamerGov
Copy link

@ad48hp I've published the project as it's own GitHub project now: https://github.com/ProGamerGov/neural-dream

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants