Skip to content

Instantly share code, notes, and snippets.

View sriharsha0806's full-sized avatar

sriharsha annamaneni sriharsha0806

View GitHub Profile
@sriharsha0806
sriharsha0806 / Tutorial_1
Created September 18, 2016 06:28
Welcome to the Tutorial wiki! I have used the following reference to learn python programming "https://github.com/kuleshov/cs228-material/blob/master/tutorials/python/cs228-python-tutorial.ipynb" Some commands are not working like s.replace() of string operations.
{
"cells": [
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"collapsed": false
},
"outputs": [
{
{
"cells": [
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
name: "segnet"
layer {
name: "data"
type: "DenseImageData"
top: "data"
top: "label"
dense_image_data_param {
source: "/SegNet/CamVid/test.txt" # Change this to the absolute path to your data file
batch_size: 8 # Change this to be the number of Monte Carlo Dropout samples you wish to make
}
name: "VGG_ILSVRC_16_layer"
layer {
name: "data"
type: "DenseImageData"
top: "data"
top: "label"
dense_image_data_param {
source: "/SegNet/CamVid/test.txt" # Change this to the absolute path to your data file
batch_size: 4 # Change this to be the number of Monte Carlo Dropout samples you wish to make
}
name: "segnet"
layer {
name: "data"
type: "DenseImageData"
top: "data"
top: "label"
dense_image_data_param {
source: "/SegNet/CamVid/test.txt" # Change this to the absolute path to your data file
batch_size: 1
}
name: "segnet"
input:"data"
input_dim: 1
input_dim: 3
input_dim: 224
input_dim: 224
layer {
name: "norm"
type: "LRN"
bottom: "data"
#
input: "data"
input_dim: 1
input_dim: 3
input_dim: 473
input_dim: 473
layer {
name: "conv1_1_3x3_s2"
type: "Convolution"
#
input: "data"
input_dim: 1
input_dim: 3
input_dim: 1024
input_dim: 2048
layer {
name: "data_sub1"
type: "Scale"
@sriharsha0806
sriharsha0806 / fcn
Last active December 15, 2017 05:54
name: "VOC-fcn8"
input:"data"
input_dim: 1
input_dim: 3
input_dim: 500
input_dim: 500
layer {
name: "conv1_1"
type: "Convolution"
name: "VOC-fcn32"
input:"data"
input_dim: 1
input_dim: 3
input_dim: 500
input_dim: 500
layer {
name: "conv1_1"
type: "Convolution"