Skip to content

Instantly share code, notes, and snippets.

View bpinaya's full-sized avatar
🤖
yes HelloWorld | head -10

Benjamin Pinaya bpinaya

🤖
yes HelloWorld | head -10
33 followers · 13 following
View GitHub Profile
@bpinaya
bpinaya / pspnet101_cityscapes_713.prototxt
Last active October 17, 2018 13:44
PSPNet Cityscapes for Netscope visualization (No BN layer, use for flow only, used in different caffe fork, check the source repo for more info https://github.com/hszhao/PSPNet). Netscope visualization https://ethereon.github.io/netscope/#/gist/68655ebb16c4274e313f060df0cf7dba
#
input: "data"
input_dim: 1
input_dim: 3
input_dim: 713
input_dim: 713
layer {
name: "conv1_1_3x3_s2"
type: "Convolution"
@bpinaya
bpinaya / VOCSegmentation.ipynb
Last active November 16, 2018 14:40
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@bpinaya
bpinaya / VOCDetection.ipynb
Created November 19, 2018 09:31
VOCDetection
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@bpinaya
bpinaya / fcnvgg8deploy.prototxt
Last active November 22, 2018 13:33
Taken from https://github.com/shelhamer/fcn.berkeleyvision.org, to see netscope check: https://ethereon.github.io/netscope/#/gist/32fe4478ff0a3c47bdfb5b4d42be41f2
name: "FCNVGG8"
layer {
name: "input"
type: "Input"
top: "data"
input_param {
# These dimensions are purely for sake of example;
# see infer.py for how to reshape the net to the given input size.
shape { dim: 1 dim: 3 dim: 500 dim: 500 }
}
@bpinaya
bpinaya / fcnvgg16train.prototxt
Last active November 29, 2018 10:53
Taken from https://github.com/shelhamer/fcn.berkeleyvision.org, to see netscope check: https://ethereon.github.io/netscope/#/gist/1c3ec567234661b63f9c3536a8846589
name: "FCNVGG16Train"
layer {
name: "input"
type: "Input"
top: "data"
top: "label"
input_param {
# These dimensions are purely for sake of example;
# see infer.py for how to reshape the net to the given input size.
shape { dim: 1 dim: 3 dim: 500 dim: 500 }
@bpinaya
bpinaya / VocDetection2010Latest.ipynb
Created December 6, 2018 12:48
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@bpinaya
bpinaya / VocDetection2012Latest.ipynb
Created December 6, 2018 12:52
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@bpinaya
bpinaya / .clang-format-5-0-chromium
Created December 19, 2018 10:08
Clang-format dump of different formats (https://clang.llvm.org/docs/ClangFormat.html)
---
Language: Cpp
# BasedOnStyle: Chromium
AccessModifierOffset: -1
AlignAfterOpenBracket: Align
AlignConsecutiveAssignments: false
AlignConsecutiveDeclarations: false
AlignEscapedNewlines: Left
AlignOperands: true
AlignTrailingComments: true
@bpinaya
bpinaya / FCN2sVGG16..prototxt
Created April 25, 2019 09:58
layer {
name: "input"
type: "Input"
top: "data"
input_param {
shape { dim: 1 dim: 3 dim: 500 dim: 500 }
}
}
layer {
name: "conv1_1"