This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
5479e1a1b1e3b43af976af6ce46691835591e2daf8c73829b9d6c97d095c14427338a12829b5476b7a8397246b1a79c059613400275c047b4094558984255095 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
name: "ERFNet" | |
# initialization is based on Enet (pytorch of ERFNet has its own default initialization method) | |
layer { | |
name: "data" | |
type: "Input" | |
top: "data" | |
input_param { | |
shape { | |
dim: 1 | |
dim: 3 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# | |
input: "data" | |
input_dim: 1 | |
input_dim: 3 | |
input_dim: 1024 | |
input_dim: 2048 | |
layer { | |
name: "data_sub1" | |
type: "Scale" |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
name: "ENet" | |
input:"data" | |
input_dim: 1 | |
input_dim: 3 | |
input_dim: 512 | |
input_dim: 512 | |
layer { | |
name: "conv0_1" | |
type: "Convolution" | |
bottom: "data" |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
name: "VOC-fcn16" | |
input: "data" | |
input_dim: 1 | |
input_dim: 3 | |
input_dim: 500 | |
input_dim: 500 | |
layer { | |
name: "conv1_1" | |
type: "Convolution" |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
name: "VOC-fcn32" | |
input:"data" | |
input_dim: 1 | |
input_dim: 3 | |
input_dim: 500 | |
input_dim: 500 | |
layer { | |
name: "conv1_1" | |
type: "Convolution" |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
name: "VOC-fcn8" | |
input:"data" | |
input_dim: 1 | |
input_dim: 3 | |
input_dim: 500 | |
input_dim: 500 | |
layer { | |
name: "conv1_1" | |
type: "Convolution" |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# | |
input: "data" | |
input_dim: 1 | |
input_dim: 3 | |
input_dim: 1024 | |
input_dim: 2048 | |
layer { | |
name: "data_sub1" | |
type: "Scale" |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# | |
input: "data" | |
input_dim: 1 | |
input_dim: 3 | |
input_dim: 473 | |
input_dim: 473 | |
layer { | |
name: "conv1_1_3x3_s2" | |
type: "Convolution" |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
name: "segnet" | |
input:"data" | |
input_dim: 1 | |
input_dim: 3 | |
input_dim: 224 | |
input_dim: 224 | |
layer { | |
name: "norm" | |
type: "LRN" | |
bottom: "data" |
NewerOlder