如何以 HDF5 格式提供 caffe 多标签数据？

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，似乎 HDF5 是更好的方法。但后来我陷入了这样的错误：

precision_layer.cpp:34] 检查失败：outer_num_ * inner_num_ == bottom[1]->count()（50 vs. 200）标签数量必须与预测数量匹配；例如，如果标签轴 == 1 并且预测形状为 (N, C, H, W)，则标签计数（标签数量）必须为N*H*W，整数值为 {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')

我的网络是由以下内容生成的：

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内容放入整数而不是数组中，但如果我这样做，caffe 会抱怨数据数量和标签不相等，然后存在。

那么，输入多标签数据的正确格式是什么？

另外，我很想知道为什么没有人简单地编写 HDF5 映射到 caffe blob 的数据格式？

回答这个问题的标题：

HDF5 文件的根目录中应有两个数据集，分别命名为“data”和“label”。形状是（data amount, dimension）。我只使用一维数据，所以我不确定顺序是什么channel, width, and height。也许这并不重要。dtype应该是浮动或双精度。

创建训练集的示例代码h5py is:

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()
  

此外，不需要精度层，只需将其删除即可。下一个问题是损失层。自从SoftmaxWithLoss只有一个输出（具有最大值的维度的索引），它不能用于多标签问题。感谢 Adian 和 Shai，我发现SigmoidCrossEntropyLoss在这种情况下很好。

下面是完整的代码，从数据创建、训练网络到获取测试结果：

main.py（根据caffelanet示例修改）

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 文件仅包含每行中 h5 文件的路径：

火车.h5list

/home/foo/bar/project/train.h5

测试.h5列表

/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
  

Converge graph:

上一批结果：

[[ 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地方需要改进。任何建议表示赞赏。