Top 1.7% dependent packages on proxy.golang.org
Top 1.7% dependent repos on proxy.golang.org
proxy.golang.org : github.com/emer/vision
Package vision is a repository containing visual processing packages in Go (golang), focused mainly on providing efficient V1 (primary visual cortex) level filtering of images, with the output then suitable as input for neural networks. Two main types of filters are supported: * **Gabor** filters simulate V1 simple-cell responses in terms of an oriented sine wave times a gaussian envelope that localizes the filter in space. This produces an edge detector that detects oriented contrast transitions between light and dark. In general, the main principle of primary visual filtering is to focus on spatial (and temporal) changes, while filtering out static, uniform areas. * **DoG** (difference of gaussian) filters simulate retinal On-center vs. Off-center contrast coding cells -- unlike gabor filters, these do not have orientation tuning. Mathematically, they are a difference between a narrow (center) vs wide (surround) gaussian, of opposite signs, balanced so that a uniform input generates offsetting values that sum to zero. In the visual system, orientation tuning is constructed from aligned DoG-like inputs, but it is more efficient to just use the Gabor filters directly. However, DoG filters capture the "blob" cells that encode color contrasts. The `vfilter` package contains general-purpose filtering code that applies (convolves) any given filter with a visual input. It also supports converting an `image.Image` into a `etensor.Float32` tensor which is the main data type used in this framework. It also supports max-pooling for efficiently reducing the dimensionality of inputs. The `kwta` package provides an implementation of the feedforward and feedback (FFFB) inhibition dynamics (and noisy X-over-X-plus-1 activation function) from the `Leabra` algorithm to produce a k-Winners-Take-All processing of visual filter outputs -- this increases the contrast and simplifies the representations, and is a good model of the dynamics in primary visual cortex.
Registry
-
Source
- Documentation
- JSON
purl: pkg:golang/github.com/emer/vision
License: BSD-3-Clause
Latest release: almost 2 years ago
First release: almost 6 years ago
Namespace: github.com/emer
Dependent packages: 11
Dependent repositories: 9
Stars: 8 on GitHub
Forks: 2 on GitHub
See more repository details: repos.ecosyste.ms
Last synced: 19 days ago
github.com/emer/axon v1.8.20
Package axon is the overall repository for all standard Axon algorithm code implemented in the Go...273 versions - Latest release: almost 2 years ago - 3 dependent packages - 5 dependent repositories - 26 stars on GitHub
github.com/CompCogNeuro/sims v1.3.5
These models are implemented in the new *Go* (golang) version of [emergent](https://github.com/em...33 versions - Latest release: almost 2 years ago - 160 stars on GitHub
github.com/compcogneuro/sims v1.3.5
These models are implemented in the new *Go* (golang) version of [emergent](https://github.com/em...33 versions - Latest release: almost 2 years ago - 160 stars on GitHub
github.com/ccnlab/lvis/sims v0.0.0-20230913171356-a39741f49e85
The Leabra Vision (LVis -- say it out loud..) model1 version - Latest release: about 2 years ago - 2 stars on GitHub
github.com/emer/envs v1.0.9
package envs is a dummy placeholder so you don't get warning errors about no .go files. see the s...10 versions - Latest release: about 2 years ago - 1 dependent package - 1 stars on GitHub
github.com/emer/auditory v1.8.1
auditory is the our repository for audition processing code in Go (golang) focused on filtering s...42 versions - Latest release: over 3 years ago - 1 dependent package - 1 dependent repositories - 7 stars on GitHub
github.com/ccnlab/deep-obj-cat/sims v0.0.0-20220502192349-d859baf8dc06
DeepLeabra object categorization project, including simulations, paper, and shape similarity expts1 version - Latest release: over 3 years ago - 3 stars on GitHub
github.com/ccnlab/deep-obj-cat/sims/wwi3d v0.0.0-20210430022006-f290f278b590
wwi3d does deep predictive learning of 3D objects tumbling through space, with periodic saccadic ...1 version - Latest release: over 4 years ago - 3 stars on GitHub
github.com/CompCogNeuro/axon v1.2.5
These models are implemented in the new *Go* (golang) version of [emergent](https://github.com/em...24 versions - Latest release: over 4 years ago - 4 stars on GitHub
github.com/compcogneuro/axon v1.2.5
These models are implemented in the new *Go* (golang) version of [emergent](https://github.com/em...24 versions - Latest release: over 4 years ago - 4 stars on GitHub
Check this option to include packages that no longer depend on this package in their latest version but previously did.