taey16

-- suppose you have a model called model
lrs_model = model:clone()
lrs = lrs_model:getParameters()
lrs:fill(1) -- setting the base learning rate to 1

-- now lets set the learning rate factor of the bias of module 5 to 2
lrs_model:get(5).bias:fill(2)
-- same thing for the weights of module 2, let's set them to 3
lrs_model:get(2).weight:fill(3)

taey16

#!/usr/bin/env python
import numpy
import sys
import timeit

try:
  import numpy.core._dotblas
  print 'FAST BLAS'
except ImportError:
  print 'slow blas'

taey16

require 'loadcaffe'
require 'nn'

local model_root = '/storage/models/vgg'
local deploy_file = paths.concat(model_root, 'vgg_layer16_deploy.prototxt')
local weight_file = paths.concat(model_root, 'vgg_layer16.caffemodel')
local model = loadcaffe.load(deploy_file, weight_file, nn)

return model

taey16

require 'nn'

-- you just need to provide the linear module you want to convert,
-- and the dimensions of the field of view of the linear layer
function convertLinear2Conv1x1(linmodule,in_size)
   local s_in = linmodule.weight:size(2)/(in_size[1]*in_size[2])
   local s_out = linmodule.weight:size(1)
   local convmodule = nn.SpatialConvolutionMM(s_in,s_out,in_size[1],in_size[2],1,1)
   convmodule.weight:copy(linmodule.weight)
   convmodule.bias:copy(linmodule.bias)

taey16

import numpy as np
import sys
import scipy.io as sio

def sample(hprev, xt, n):
  for index in xt:
    x = np.zeros((vocab_size, 1))
    x[index] = 1
    h = np.tanh(np.dot(Wxh, x) + np.dot(Whh, hprev) + bh)
    y = np.dot(Why, h) + by

taey16

import numpy as np
import sys
import caffe
from caffe import caffe_utils as utils
import datetime

CAFFE_ROOT='/works/caffe/'

MODEL_DEPLOY_FILE = \
  #'/storage/ImageNet/ILSVRC2012/model/resnet/ResNet_caffe_models/ResNet-50-deploy.prototxt'