Heitor Rapela Medeiros

If you still want, you can checkout this link: [Computing per unit visualizations](https://github.com/yosinski/deep-visualization-toolbox/blob/master/doc/computing_per_unit_visualizations.md). I tried here and I could generate an Image of the pool5/7x7_s1. Now, I'm trying to put...

Nice one, I had to do the same for my research. 😉 I will try it after this period.

"File "/home/deep/Downloads/caffe-master/python/caffe/io.py", line 259, in set_mean raise ValueError('Mean shape incompatible with input shape.') ValueError: Mean shape incompatible with input shape." Try to use --data-size "(224,224)", and checkout this [link](https://stackoverflow.com/questions/30808735/error-when-using-classify-in-caffe) `./optimize_image.py...

"@visonpon can you give examples of the script usage like use the optimize_image.py script?" Answer this question, you can see this [link](https://github.com/yosinski/deep-visualization-toolbox/blob/master/doc/running-optimize-image.md): `./optimize_image.py --decay 0.0001 --blur-radius 1.0 --blur-every 4 --max-iter...

@visonpon 1. how to use the crop_max_patches.py? can you give examples of the script usage like use the optimize_image.py script? - `python crop_max_patches.py output.pkl '../models/bvlc-googlenet/deploy.prototxt' '../models/bvlc-googlenet/bvlc_googlenet.caffemodel' '../input_images/' 'out.txt' 'outputFolder' 'pool5/7x7_s1'...

Hey there, checkout this link, maybe it could help you. [Running Optimize Image](https://github.com/yosinski/deep-visualization-toolbox/blob/master/doc/running-optimize-image.md)

I'm running the deep-visualization-toolbox with googLeNet. I had this error too, but I correct it. Check this [StackOverflow](https://stackoverflow.com/questions/30808735/error-when-using-classify-in-caffe): You need to replace some lines in: caffe/python/caffe/io.py.

I was getting NAN for a custom dataset under the amp = True flag also (version [0.27.9](https://github.com/lucidrains/denoising-diffusion-pytorch/commit/e0a1bed31a29cfc1170c83bd99d5d5b2edefcabf)). So, I changed the flag to false and the training is doing good.

No

Hello, @williamFalcon and @hanlint. Do you have any news about this feature? I am using pytorch lightning, but I think it would be useful to add mosaic training strategies like...