如何以HDF5格式提供caffe多标签数据？
How to feed caffe multi label data in HDF5 format?
我想将 caffe 与矢量标签一起使用，而不是整数。我检查了一些答案，HDF5 似乎是更好的方法。但是后来我遇到了这样的错误：
accuracy_layer.cpp:34] Check failed: outer_num_ * inner_num_ == bottom[1]->count() (50 vs. 200) Number of labels must match number of predictions; e.g., if label axis == 1 and prediction shape is (N, C, H, W), label count (number of labels) must be N*H*W, with integer values in {0, 1, ..., C-1}.
HDF5 创建为：
f = h5py.File('train.h5', 'w')
f.create_dataset('data', (1200, 128), dtype='f8')
f.create_dataset('label', (1200, 4), dtype='f4')
我的网络是由：
生成的
def net(hdf5, batch_size):
n = caffe.NetSpec()
n.data, n.label = L.HDF5Data(batch_size=batch_size, source=hdf5, ntop=2)
n.ip1 = L.InnerProduct(n.data, num_output=50, weight_filler=dict(type='xavier'))
n.relu1 = L.ReLU(n.ip1, in_place=True)
n.ip2 = L.InnerProduct(n.relu1, num_output=50, weight_filler=dict(type='xavier'))
n.relu2 = L.ReLU(n.ip2, in_place=True)
n.ip3 = L.InnerProduct(n.relu1, num_output=4, weight_filler=dict(type='xavier'))
n.accuracy = L.Accuracy(n.ip3, n.label)
n.loss = L.SoftmaxWithLoss(n.ip3, n.label)
return n.to_proto()
with open(PROJECT_HOME + 'auto_train.prototxt', 'w') as f:
f.write(str(net('/home/romulus/code/project/train.h5list', 50)))
with open(PROJECT_HOME + 'auto_test.prototxt', 'w') as f:
f.write(str(net('/home/romulus/code/project/test.h5list', 20)))
看来我应该增加标签数量并将东西放在整数而不是数组中，但是如果我这样做，caffe 会抱怨数据数量和标签不相等，然后存在。
那么，提供多标签数据的正确格式是什么？
此外，我很想知道为什么没有人只是简单地写下 HDF5 如何映射到 caffe blob 的数据格式？
您的准确性层毫无意义。
精度层的工作方式：在caffe精度层中需要两个输入
(i) 预测概率 vector and
(ii) ground-truth 对应 scalar integer label.
准确性层然后检查预测标签的概率是否确实是最大的（或在 top_k 内）。
因此，如果您必须对 C 不同的 类 进行分类，您的输入将是 N-by-C（其中 N 是批量大小）输入预测N 个样本属于 C 类 和 N 个标签的概率。
它在您的网络中定义的方式：您输入准确度层 N-by-4 预测和 N-by-4 标签 - - 这对咖啡没有意义。
回答这个问题的标题：
HDF5 文件应该在根目录下有两个数据集，分别命名为"data" 和"label"。形状是（data amount，dimension）。我只使用 one-dimension 数据，所以我不确定 channel、width 和 height 的顺序是什么。也许没关系。 dtype 应该是 float 或 double。
使用 h5py 创建训练集的示例代码是：
import h5py, os
import numpy as np
f = h5py.File('train.h5', 'w')
# 1200 data, each is a 128-dim vector
f.create_dataset('data', (1200, 128), dtype='f8')
# Data's labels, each is a 4-dim vector
f.create_dataset('label', (1200, 4), dtype='f4')
# Fill in something with fixed pattern
# Regularize values to between 0 and 1, or SigmoidCrossEntropyLoss will not work
for i in range(1200):
a = np.empty(128)
if i % 4 == 0:
for j in range(128):
a[j] = j / 128.0;
l = [1,0,0,0]
elif i % 4 == 1:
for j in range(128):
a[j] = (128 - j) / 128.0;
l = [1,0,1,0]
elif i % 4 == 2:
for j in range(128):
a[j] = (j % 6) / 128.0;
l = [0,1,1,0]
elif i % 4 == 3:
for j in range(128):
a[j] = (j % 4) * 4 / 128.0;
l = [1,0,1,1]
f['data'][i] = a
f['label'][i] = l
f.close()
另外，不需要精度层，直接去掉就好了。下一个问题是损失层。由于 SoftmaxWithLoss 只有一个输出（具有最大值的维度的索引），因此不能用于 multi-label 问题。感谢 Adian 和 Shai，我发现 SigmoidCrossEntropyLoss 在这种情况下很好。
以下是完整代码，从数据创建、训练网络到获取测试结果：
main.py (modified from caffe lanet example)
import os, sys
PROJECT_HOME = '.../project/'
CAFFE_HOME = '.../caffe/'
os.chdir(PROJECT_HOME)
sys.path.insert(0, CAFFE_HOME + 'caffe/python')
import caffe, h5py
from pylab import *
from caffe import layers as L
def net(hdf5, batch_size):
n = caffe.NetSpec()
n.data, n.label = L.HDF5Data(batch_size=batch_size, source=hdf5, ntop=2)
n.ip1 = L.InnerProduct(n.data, num_output=50, weight_filler=dict(type='xavier'))
n.relu1 = L.ReLU(n.ip1, in_place=True)
n.ip2 = L.InnerProduct(n.relu1, num_output=50, weight_filler=dict(type='xavier'))
n.relu2 = L.ReLU(n.ip2, in_place=True)
n.ip3 = L.InnerProduct(n.relu2, num_output=4, weight_filler=dict(type='xavier'))
n.loss = L.SigmoidCrossEntropyLoss(n.ip3, n.label)
return n.to_proto()
with open(PROJECT_HOME + 'auto_train.prototxt', 'w') as f:
f.write(str(net(PROJECT_HOME + 'train.h5list', 50)))
with open(PROJECT_HOME + 'auto_test.prototxt', 'w') as f:
f.write(str(net(PROJECT_HOME + 'test.h5list', 20)))
caffe.set_device(0)
caffe.set_mode_gpu()
solver = caffe.SGDSolver(PROJECT_HOME + 'auto_solver.prototxt')
solver.net.forward()
solver.test_nets[0].forward()
solver.step(1)
niter = 200
test_interval = 10
train_loss = zeros(niter)
test_acc = zeros(int(np.ceil(niter * 1.0 / test_interval)))
print len(test_acc)
output = zeros((niter, 8, 4))
# The main solver loop
for it in range(niter):
solver.step(1) # SGD by Caffe
train_loss[it] = solver.net.blobs['loss'].data
solver.test_nets[0].forward(start='data')
output[it] = solver.test_nets[0].blobs['ip3'].data[:8]
if it % test_interval == 0:
print 'Iteration', it, 'testing...'
correct = 0
data = solver.test_nets[0].blobs['ip3'].data
label = solver.test_nets[0].blobs['label'].data
for test_it in range(100):
solver.test_nets[0].forward()
# Positive values map to label 1, while negative values map to label 0
for i in range(len(data)):
for j in range(len(data[i])):
if data[i][j] > 0 and label[i][j] == 1:
correct += 1
elif data[i][j] %lt;= 0 and label[i][j] == 0:
correct += 1
test_acc[int(it / test_interval)] = correct * 1.0 / (len(data) * len(data[0]) * 100)
# Train and test done, outputing convege graph
_, ax1 = subplots()
ax2 = ax1.twinx()
ax1.plot(arange(niter), train_loss)
ax2.plot(test_interval * arange(len(test_acc)), test_acc, 'r')
ax1.set_xlabel('iteration')
ax1.set_ylabel('train loss')
ax2.set_ylabel('test accuracy')
_.savefig('converge.png')
# Check the result of last batch
print solver.test_nets[0].blobs['ip3'].data
print solver.test_nets[0].blobs['label'].data
h5list 文件只在每一行中包含 h5 文件的路径：
train.h5list
/home/foo/bar/project/train.h5
test.h5list
/home/foo/bar/project/test.h5
和求解器：
auto_solver.prototxt
train_net: "auto_train.prototxt"
test_net: "auto_test.prototxt"
test_iter: 10
test_interval: 20
base_lr: 0.01
momentum: 0.9
weight_decay: 0.0005
lr_policy: "inv"
gamma: 0.0001
power: 0.75
display: 100
max_iter: 10000
snapshot: 5000
snapshot_prefix: "sed"
solver_mode: GPU
最后一批结果：
[[ 35.91593933 -37.46276474 -6.2579031 -6.30313492]
[ 42.69248581 -43.00864792 13.19664764 -3.35134125]
[ -1.36403108 1.38531208 2.77786589 -0.34310576]
[ 2.91686511 -2.88944006 4.34043217 0.32656598]
...
[ 35.91593933 -37.46276474 -6.2579031 -6.30313492]
[ 42.69248581 -43.00864792 13.19664764 -3.35134125]
[ -1.36403108 1.38531208 2.77786589 -0.34310576]
[ 2.91686511 -2.88944006 4.34043217 0.32656598]]
[[ 1. 0. 0. 0.]
[ 1. 0. 1. 0.]
[ 0. 1. 1. 0.]
[ 1. 0. 1. 1.]
...
[ 1. 0. 0. 0.]
[ 1. 0. 1. 0.]
[ 0. 1. 1. 0.]
[ 1. 0. 1. 1.]]
我认为这段代码还有很多需要改进的地方。任何建议表示赞赏。
我想将 caffe 与矢量标签一起使用，而不是整数。我检查了一些答案，HDF5 似乎是更好的方法。但是后来我遇到了这样的错误：
accuracy_layer.cpp:34] Check failed:
outer_num_ * inner_num_ == bottom[1]->count()(50 vs. 200) Number of labels must match number of predictions; e.g., if label axis == 1 and prediction shape is (N, C, H, W), label count (number of labels) must beN*H*W, with integer values in {0, 1, ..., C-1}.
HDF5 创建为：
f = h5py.File('train.h5', 'w')
f.create_dataset('data', (1200, 128), dtype='f8')
f.create_dataset('label', (1200, 4), dtype='f4')
我的网络是由：
生成的def net(hdf5, batch_size):
n = caffe.NetSpec()
n.data, n.label = L.HDF5Data(batch_size=batch_size, source=hdf5, ntop=2)
n.ip1 = L.InnerProduct(n.data, num_output=50, weight_filler=dict(type='xavier'))
n.relu1 = L.ReLU(n.ip1, in_place=True)
n.ip2 = L.InnerProduct(n.relu1, num_output=50, weight_filler=dict(type='xavier'))
n.relu2 = L.ReLU(n.ip2, in_place=True)
n.ip3 = L.InnerProduct(n.relu1, num_output=4, weight_filler=dict(type='xavier'))
n.accuracy = L.Accuracy(n.ip3, n.label)
n.loss = L.SoftmaxWithLoss(n.ip3, n.label)
return n.to_proto()
with open(PROJECT_HOME + 'auto_train.prototxt', 'w') as f:
f.write(str(net('/home/romulus/code/project/train.h5list', 50)))
with open(PROJECT_HOME + 'auto_test.prototxt', 'w') as f:
f.write(str(net('/home/romulus/code/project/test.h5list', 20)))
看来我应该增加标签数量并将东西放在整数而不是数组中，但是如果我这样做，caffe 会抱怨数据数量和标签不相等，然后存在。
那么，提供多标签数据的正确格式是什么？
此外，我很想知道为什么没有人只是简单地写下 HDF5 如何映射到 caffe blob 的数据格式？
您的准确性层毫无意义。
精度层的工作方式：在caffe精度层中需要两个输入
(i) 预测概率 vector and
(ii) ground-truth 对应 scalar integer label.
准确性层然后检查预测标签的概率是否确实是最大的（或在 top_k 内）。
因此，如果您必须对 C 不同的 类 进行分类，您的输入将是 N-by-C（其中 N 是批量大小）输入预测N 个样本属于 C 类 和 N 个标签的概率。
它在您的网络中定义的方式：您输入准确度层 N-by-4 预测和 N-by-4 标签 - - 这对咖啡没有意义。
回答这个问题的标题：
HDF5 文件应该在根目录下有两个数据集，分别命名为"data" 和"label"。形状是（data amount，dimension）。我只使用 one-dimension 数据，所以我不确定 channel、width 和 height 的顺序是什么。也许没关系。 dtype 应该是 float 或 double。
使用 h5py 创建训练集的示例代码是：
import h5py, os
import numpy as np
f = h5py.File('train.h5', 'w')
# 1200 data, each is a 128-dim vector
f.create_dataset('data', (1200, 128), dtype='f8')
# Data's labels, each is a 4-dim vector
f.create_dataset('label', (1200, 4), dtype='f4')
# Fill in something with fixed pattern
# Regularize values to between 0 and 1, or SigmoidCrossEntropyLoss will not work
for i in range(1200):
a = np.empty(128)
if i % 4 == 0:
for j in range(128):
a[j] = j / 128.0;
l = [1,0,0,0]
elif i % 4 == 1:
for j in range(128):
a[j] = (128 - j) / 128.0;
l = [1,0,1,0]
elif i % 4 == 2:
for j in range(128):
a[j] = (j % 6) / 128.0;
l = [0,1,1,0]
elif i % 4 == 3:
for j in range(128):
a[j] = (j % 4) * 4 / 128.0;
l = [1,0,1,1]
f['data'][i] = a
f['label'][i] = l
f.close()
另外，不需要精度层，直接去掉就好了。下一个问题是损失层。由于 SoftmaxWithLoss 只有一个输出（具有最大值的维度的索引），因此不能用于 multi-label 问题。感谢 Adian 和 Shai，我发现 SigmoidCrossEntropyLoss 在这种情况下很好。
以下是完整代码，从数据创建、训练网络到获取测试结果：
main.py (modified from caffe lanet example)
import os, sys
PROJECT_HOME = '.../project/'
CAFFE_HOME = '.../caffe/'
os.chdir(PROJECT_HOME)
sys.path.insert(0, CAFFE_HOME + 'caffe/python')
import caffe, h5py
from pylab import *
from caffe import layers as L
def net(hdf5, batch_size):
n = caffe.NetSpec()
n.data, n.label = L.HDF5Data(batch_size=batch_size, source=hdf5, ntop=2)
n.ip1 = L.InnerProduct(n.data, num_output=50, weight_filler=dict(type='xavier'))
n.relu1 = L.ReLU(n.ip1, in_place=True)
n.ip2 = L.InnerProduct(n.relu1, num_output=50, weight_filler=dict(type='xavier'))
n.relu2 = L.ReLU(n.ip2, in_place=True)
n.ip3 = L.InnerProduct(n.relu2, num_output=4, weight_filler=dict(type='xavier'))
n.loss = L.SigmoidCrossEntropyLoss(n.ip3, n.label)
return n.to_proto()
with open(PROJECT_HOME + 'auto_train.prototxt', 'w') as f:
f.write(str(net(PROJECT_HOME + 'train.h5list', 50)))
with open(PROJECT_HOME + 'auto_test.prototxt', 'w') as f:
f.write(str(net(PROJECT_HOME + 'test.h5list', 20)))
caffe.set_device(0)
caffe.set_mode_gpu()
solver = caffe.SGDSolver(PROJECT_HOME + 'auto_solver.prototxt')
solver.net.forward()
solver.test_nets[0].forward()
solver.step(1)
niter = 200
test_interval = 10
train_loss = zeros(niter)
test_acc = zeros(int(np.ceil(niter * 1.0 / test_interval)))
print len(test_acc)
output = zeros((niter, 8, 4))
# The main solver loop
for it in range(niter):
solver.step(1) # SGD by Caffe
train_loss[it] = solver.net.blobs['loss'].data
solver.test_nets[0].forward(start='data')
output[it] = solver.test_nets[0].blobs['ip3'].data[:8]
if it % test_interval == 0:
print 'Iteration', it, 'testing...'
correct = 0
data = solver.test_nets[0].blobs['ip3'].data
label = solver.test_nets[0].blobs['label'].data
for test_it in range(100):
solver.test_nets[0].forward()
# Positive values map to label 1, while negative values map to label 0
for i in range(len(data)):
for j in range(len(data[i])):
if data[i][j] > 0 and label[i][j] == 1:
correct += 1
elif data[i][j] %lt;= 0 and label[i][j] == 0:
correct += 1
test_acc[int(it / test_interval)] = correct * 1.0 / (len(data) * len(data[0]) * 100)
# Train and test done, outputing convege graph
_, ax1 = subplots()
ax2 = ax1.twinx()
ax1.plot(arange(niter), train_loss)
ax2.plot(test_interval * arange(len(test_acc)), test_acc, 'r')
ax1.set_xlabel('iteration')
ax1.set_ylabel('train loss')
ax2.set_ylabel('test accuracy')
_.savefig('converge.png')
# Check the result of last batch
print solver.test_nets[0].blobs['ip3'].data
print solver.test_nets[0].blobs['label'].data
h5list 文件只在每一行中包含 h5 文件的路径：
train.h5list
/home/foo/bar/project/train.h5
test.h5list
/home/foo/bar/project/test.h5
和求解器：
auto_solver.prototxt
train_net: "auto_train.prototxt" test_net: "auto_test.prototxt" test_iter: 10 test_interval: 20 base_lr: 0.01 momentum: 0.9 weight_decay: 0.0005 lr_policy: "inv" gamma: 0.0001 power: 0.75 display: 100 max_iter: 10000 snapshot: 5000 snapshot_prefix: "sed" solver_mode: GPU
最后一批结果：
[[ 35.91593933 -37.46276474 -6.2579031 -6.30313492] [ 42.69248581 -43.00864792 13.19664764 -3.35134125] [ -1.36403108 1.38531208 2.77786589 -0.34310576] [ 2.91686511 -2.88944006 4.34043217 0.32656598] ... [ 35.91593933 -37.46276474 -6.2579031 -6.30313492] [ 42.69248581 -43.00864792 13.19664764 -3.35134125] [ -1.36403108 1.38531208 2.77786589 -0.34310576] [ 2.91686511 -2.88944006 4.34043217 0.32656598]] [[ 1. 0. 0. 0.] [ 1. 0. 1. 0.] [ 0. 1. 1. 0.] [ 1. 0. 1. 1.] ... [ 1. 0. 0. 0.] [ 1. 0. 1. 0.] [ 0. 1. 1. 0.] [ 1. 0. 1. 1.]]
我认为这段代码还有很多需要改进的地方。任何建议表示赞赏。