issues
search
LumenPallidium
/
neural-file-sorter
A neural network based file sorter. Trains an autoencoder to sort images or audio based on the similarity of their encodings, or uses the OpenAI CLIP model.
MIT License
27
stars
1
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Overhaul
#20
LumenPallidium
closed
1 year ago
0
no clip labels question
#19
sneccc
opened
1 year ago
3
clip_categories
#18
sneccc
closed
1 year ago
1
change final poolingfunction to control h,w size (instead of defaulting to 1,1)
#17
LumenPallidium
closed
3 years ago
1
make encode_image a method on the autoencoder class
#16
LumenPallidium
closed
3 years ago
1
add variational autoencoder
#15
LumenPallidium
closed
3 years ago
1
add train, test, val split options, as well as dataset shuffling
#14
LumenPallidium
opened
3 years ago
0
fp16 or mixed-precision computation
#13
LumenPallidium
opened
3 years ago
0
Add CLIP related features
#12
LumenPallidium
opened
3 years ago
1
Add requirements.txt
#11
LumenPallidium
closed
1 year ago
1
complete the de-encoding k-mean centroid functionality
#10
LumenPallidium
opened
3 years ago
2
add dashboard button and callback to see the autoencoding of a selected point
#9
LumenPallidium
opened
3 years ago
0
beautify dashboard
#8
LumenPallidium
opened
3 years ago
0
Method to enter new image path, run through encoder, and see its embedding in the dash
#7
LumenPallidium
opened
3 years ago
0
add data augementation and transformation options
#6
LumenPallidium
opened
3 years ago
3
add more loss functions and optimizers
#5
LumenPallidium
opened
3 years ago
2
add more embedding methods beyond locally linear embedding
#4
LumenPallidium
closed
3 years ago
1
add basic utilities for audio autoencoder
#3
LumenPallidium
opened
3 years ago
0
add resnet architecture for visual autoencoder
#2
LumenPallidium
closed
1 year ago
1
Some stride values not allowed due to deconvolution (ConvTranspose2d) output_padding
#1
LumenPallidium
closed
3 years ago
1