python caffe training solve.py
来源:互联网 发布:商品条码数据库下载 编辑:程序博客网 时间:2024/04/26 15:57
from __future__ import division
import numpy as np
import sys
caffe_root = '../../'
sys.path.insert(0, caffe_root + 'python')
import caffe
# make a bilinear interpolation kernel
# credit @longjon
def upsample_filt(size):
factor = (size + 1) // 2
if size % 2 == 1:
center = factor - 1
else:
center = factor - 0.5
og = np.ogrid[:size, :size]
return (1 - abs(og[0] - center) / factor) * \
(1 - abs(og[1] - center) / factor)
# set parameters s.t. deconvolutional layers compute bilinear interpolation
# N.B. this is for deconvolution without groups
def interp_surgery(net, layers):
for l in layers:
m, k, h, w = net.params[l][0].data.shape
if m != k:
print 'input + output channels need to be the same'
raise
if h != w:
print 'filters need to be square'
raise
filt = upsample_filt(h)
net.params[l][0].data[range(m), range(k), :, :] = filt
# base net -- follow the editing model parameters example to make
# a fully convolutional VGG16 net.
# http://nbviewer.ipython.org/github/BVLC/caffe/blob/master/examples/net_surgery.ipynb
base_weights = caffe_root+'models/5stage-vgg.caffemodel'
# init
caffe.set_mode_gpu()
caffe.set_device(0)
solver = caffe.SGDSolver('/home/tsq/Documents/project/DeepSkeleton/examples/DeepSkeleton/solver.prototxt')
# do net surgery to set the deconvolution weights for bilinear interpolation
interp_layers = [k for k in solver.net.params.keys() if 'up' in k]
interp_surgery(solver.net, interp_layers)
# copy base weights for fine-tuning
#solver.restore('dsn-full-res-3-scales_iter_29000.solverstate')
#tsqsolver.net.copy_from(base_weights)
# solve straight through -- a better approach is to define a solving loop to
# 1. take SGD steps
# 2. score the model by the test net `solver.test_nets[0]`
# 3. repeat until satisfied
solver.step(1)
import numpy as np
import sys
caffe_root = '../../'
sys.path.insert(0, caffe_root + 'python')
import caffe
# make a bilinear interpolation kernel
# credit @longjon
def upsample_filt(size):
factor = (size + 1) // 2
if size % 2 == 1:
center = factor - 1
else:
center = factor - 0.5
og = np.ogrid[:size, :size]
return (1 - abs(og[0] - center) / factor) * \
(1 - abs(og[1] - center) / factor)
# set parameters s.t. deconvolutional layers compute bilinear interpolation
# N.B. this is for deconvolution without groups
def interp_surgery(net, layers):
for l in layers:
m, k, h, w = net.params[l][0].data.shape
if m != k:
print 'input + output channels need to be the same'
raise
if h != w:
print 'filters need to be square'
raise
filt = upsample_filt(h)
net.params[l][0].data[range(m), range(k), :, :] = filt
# base net -- follow the editing model parameters example to make
# a fully convolutional VGG16 net.
# http://nbviewer.ipython.org/github/BVLC/caffe/blob/master/examples/net_surgery.ipynb
base_weights = caffe_root+'models/5stage-vgg.caffemodel'
# init
caffe.set_mode_gpu()
caffe.set_device(0)
solver = caffe.SGDSolver('/home/tsq/Documents/project/DeepSkeleton/examples/DeepSkeleton/solver.prototxt')
# do net surgery to set the deconvolution weights for bilinear interpolation
interp_layers = [k for k in solver.net.params.keys() if 'up' in k]
interp_surgery(solver.net, interp_layers)
# copy base weights for fine-tuning
#solver.restore('dsn-full-res-3-scales_iter_29000.solverstate')
#tsqsolver.net.copy_from(base_weights)
# solve straight through -- a better approach is to define a solving loop to
# 1. take SGD steps
# 2. score the model by the test net `solver.test_nets[0]`
# 3. repeat until satisfied
solver.step(1)
import matplotlib as plt
%matplotlib inline
plt.pyplot.imshow(solver.net.blobs['label'].data[0][0,:,:],cmap="gray")
0 0
- python caffe training solve.py
- FCN ---caffe运行solve.py文件报错
- solve.py 调试
- Solve import caffe error
- caffe的python接口学习(3):训练模型(training)
- caffe的python接口学习(3):训练模型(training)
- caffe的python接口学习(3):训练模型(training)
- caffe的python接口学习(3):训练模型(training)
- 解决Windows中caffe用python运行solve时kernel restart问题
- caffe draw_net.py
- caffe-fcn-net.py
- caffe-fcn-solver.py
- caffe-fcn-test.py
- caffe-seg-voc_helper.py
- caffe+py-faster-rcnn
- caffe training tricks
- Training MNIST with Caffe
- caffe的python接口中的draw_net.py使用时,错误提示及解决办法
- Java——单例模式
- unity声音管理
- LeetCode 217. Contains Duplicate 解题报告
- 键盘输入10个数,放到数组中去除该数组中大于10的数,将该数组中的数字写入到本地文件
- HTTP3xx重定向
- python caffe training solve.py
- C语言 打印菱形(可变行数)
- MySQL中函数CONCAT及GROUP_CONCAT
- poj 2230 Watchcow(欧拉回路)
- 后缀数组代码理解加注释
- 算法分析与设计-动态规划0
- C++利用socket的客户端和服务器之间传输文件
- Spring Data JPA使用JpaRepository自动装配报No qualifying bean of type错误
- 51nod 1065 最小正子段和(前缀和)