引言
记录学习官网的例程中的一些重要语句，遇到的问题等，内容分散，建议顺序查看。
主要是调用Caffe的Python接口
源文件就在{caffe_root}/examples中，安装sudo pip install jupyter打开即可运行，初学者最好是放在它指定的目录，如，否则要改很多路径。
注：eaxmples是用jupyter notebook写的，部分Cell中出现了一些特殊的用法：
1. 感叹号‘！’：用于执行系统命令，如 !pwd
2. 百分号‘%’：用法太多，如 %matplotlib inline 显示绘图窗口 详见Jupyter Notebook Viewer
目录
微调一个预训练的网络用于风格识别
1. 配置网络并下载数据集
# Helper function for deprocessing preprocessed images, e.g., for display. 逆向处理已经预处理过的图像
def deprocess_net_image(image):
image = image.copy() # don't modify destructively
image = image[::-1] # BGR -> RGB
image = image.transpose(1, 2, 0) # CHW -> HWC
image += [123, 117, 104] # (approximately) undo mean subtraction
# clamp values in [0, 255]
image[image < 0], image[image > 255] = 0, 255
# round and cast from float32 to uint8
image = np.round(image)
image = np.require(image, dtype=np.uint8)
return image2. 定义并运行网络
- 这个网络定义在写法和表现形式上和上一节有所差别，先对pycaffe的部分层定义进行融合包装，下面通过调用该函数且传入不同参数，能够实现同类型的层可以设置不同的层参数。方便快速构建多层网络。
from caffe import layers as L
from caffe import params as P
weight_param = dict(lr_mult=1, decay_mult=1)
bias_param = dict(lr_mult=2, decay_mult=0)
learned_param = [weight_param, bias_param]
frozen_param = [dict(lr_mult=0)] * 2 # 将lr_mult设置为0来冻结层参数
def conv_relu(bottom, ks, nout, stride=1, pad=0, group=1,
param=learned_param,
weight_filler=dict(type='gaussian', std=0.01),
bias_filler=dict(type='constant', value=0.1)):
conv = L.Convolution(bottom, kernel_size=ks, stride=stride,
num_output=nout, pad=pad, group=group,
param=param, weight_filler=weight_filler,
bias_filler=bias_filler)
return conv, L.ReLU(conv, in_place=True)
def fc_relu(bottom, nout, param=learned_param,
weight_filler=dict(type='gaussian', std=0.005),
bias_filler=dict(type='constant', value=0.1)):
fc = L.InnerProduct(bottom, num_output=nout, param=param,
weight_filler=weight_filler,
bias_filler=bias_filler)
return fc, L.ReLU(fc, in_place=True)
def max_pool(bottom, ks, stride=1):
return L.Pooling(bottom, pool=P.Pooling.MAX, kernel_size=ks, stride=stride)
def caffenet(data, label=None, train=True, num_classes=1000,
classifier_name='fc8', learn_all=False):
"""Returns a NetSpec specifying CaffeNet, following the original proto text
specification (./models/bvlc_reference_caffenet/train_val.prototxt)."""
n = caffe.NetSpec()
n.data = data
param = learned_param if learn_all else frozen_param
n.conv1, n.relu1 = conv_relu(n.data, 11, 96, stride=4, param=param)
n.pool1 = max_pool(n.relu1, 3, stride=2)
n.norm1 = L.LRN(n.pool1, local_size=5, alpha=1e-4, beta=0.75)
n.conv2, n.relu2 = conv_relu(n.norm1, 5, 256, pad=2, group=2, param=param)
n.pool2 = max_pool(n.relu2, 3, stride=2)
n.norm2 = L.LRN(n.pool2, local_size=5, alpha=1e-4, beta=0.75)
n.conv3, n.relu3 = conv_relu(n.norm2, 3, 384, pad=1, param=param)
n.conv4, n.relu4 = conv_relu(n.relu3, 3, 384, pad=1, group=2, param=param)
n.conv5, n.relu5 = conv_relu(n.relu4, 3, 256, pad=1, group=2, param=param)
n.pool5 = max_pool(n.relu5, 3, stride=2)
n.fc6, n.relu6 = fc_relu(n.pool5, 4096, param=param)
if train: # TEST网络少两个dropout层drop6，drop7
n.drop6 = fc7input = L.Dropout(n.relu6, in_place=True)
else:
fc7input = n.relu6
n.fc7, n.relu7 = fc_relu(fc7input, 4096, param=param)
if train:
n.drop7 = fc8input = L.Dropout(n.relu7, in_place=True)
else:
fc8input = n.relu7
# always learn fc8 (param=learned_param)
fc8 = L.InnerProduct(fc8input, num_output=num_classes, param=learned_param)
# give fc8 the name specified by argument `classifier_name` 改掉预训练网络中某一层的命名，那么该层就不会加载weights中的参数转而通过ProtoTXT指定的方式填充
n.__setattr__(classifier_name, fc8)
if not train:
n.probs = L.Softmax(fc8)
if label is not None:
n.label = label
n.loss = L.SoftmaxWithLoss(fc8, n.label)
n.acc = L.Accuracy(fc8, n.label)
# write the net to a temporary file and return its filename
with tempfile.NamedTemporaryFile(delete=False) as f:
f.write(str(n.to_proto()))
return f.name用虚拟数据(dummy data)构建一个网络
dummy_data = L.DummyData(shape=dict(dim=[1, 3, 227, 227])) imagenet_net_filename = caffenet(data=dummy_data, train=False) imagenet_net = caffe.Net(imagenet_net_filename, weights, caffe.TEST)- 用前面下载的风格数据集Flickr定义
style_net函数来调用caffenet 与
caffenet的不同之处在于：- 用
ImageData层将Flickr dataset作为网络输入 - 输入20个类别而不是原来的1000类
最后的分类层
fc8改名为fc8_flickr，以便Caffe不从预训练模型中加载权重def style_net(train=True, learn_all=False, subset=None): if subset is None: subset = 'train' if train else 'test' source = caffe_root + 'data/flickr_style/%s.txt' % subset transform_param = dict(mirror=train, crop_size=227, mean_file=caffe_root + 'data/ilsvrc12/imagenet_mean.binaryproto') style_data, style_label = L.ImageData( transform_param=transform_param, source=source, batch_size=50, new_height=256, new_width=256, ntop=2) return caffenet(data=style_data, label=style_label, train=train, num_classes=NUM_STYLE_LABELS, classifier_name='fc8_flickr', learn_all=learn_all)
- 用
- 用上面定义的
style_net函数来初始化untrained_style_net：下载的数据集作为图像输入，加载预训练模型为权重。 调用
untrained_style_net.forward()得到一个batch的训练数据untrained_style_net = caffe.Net(style_net(train=False, subset='train'), weights, caffe.TEST) untrained_style_net.forward() style_data_batch = untrained_style_net.blobs['data'].data.copy() style_label_batch = np.array(untrained_style_net.blobs['label'].data, dtype=np.int32)在
untrained_style_net的一个训练batch中随机取1张(实际选的是第8张)显示，并打印出对应标签。batch_index = 8 image = style_data_batch[batch_index] plt.imshow(deprocess_net_image(image)) print 'actual label =', style_labels[style_label_batch[batch_index]]- 把上面这幅图作为
imagenet_net的输入，然后跑一次并可视化top 5的预测类别：disp_imagenet_preds(imagenet_net, image)，调用的函数见下。 把同样的一幅图作为
untrained_style_net的输入，跑一次并可视化top5的预测类别：disp_style_preds(untrained_style_net, image)，调用的函数见下。def disp_preds(net, image, labels, k=5, name='ImageNet'): input_blob = net.blobs['data'] net.blobs['data'].data[0, ...] = image probs = net.forward(start='conv1')['probs'][0] top_k = (-probs).argsort()[:k] print 'top %d predicted %s labels =' % (k, name) print '\n'.join('\t(%d) %5.2f%% %s' % (i+1, 100*probs[p], labels[p]) for i, p in enumerate(top_k)) def disp_imagenet_preds(net, image): disp_preds(net, image, imagenet_labels, name='ImageNet') def disp_style_preds(net, image): disp_preds(net, image, style_labels, name='style')通过更改batch_index查看不同图片的预测结果发现，
imagenet_net网络会输出不同的概率，不同可能来源于对风格图像的目标识别，untrained_style_net输出概率相同，因为前面构建网络时指定了最后一个分类层为5个标签，且没加载预训练权重，也指定填充方式，因此该层权重全为零，即softmax输入全为零，最后输出的概率即为1/N，N为标签数量。还可验证
imagenet_net和untrained_style_net的fc7层的输出是一样的，因为都是加载了预训练权重。diff = untrained_style_net.blobs['fc7'].data[0] - imagenet_net.blobs['fc7'].data[0] error = (diff ** 2).sum() assert error < 1e-8- 删除
untrained_style_net节省内存：del untrained_style_net
3. 训练风格分类器
定义
solver函数来创建Caffe求解器的prototxt，返回prototxt的文件名from caffe.proto import caffe_pb2 def solver(train_net_path, test_net_path=None, base_lr=0.001): s = caffe_pb2.SolverParameter() # Specify locations of the train and (maybe) test networks. s.train_net = train_net_path if test_net_path is not None: s.test_net.append(test_net_path) s.test_interval = 1000 # Test after every 1000 training iterations. s.test_iter.append(100) # Test on 100 batches each time we test. # The number of iterations over which to average the gradient. # Effectively boosts the training batch size by the given factor, without # affecting memory utilization. s.iter_size = 1 s.max_iter = 100000 # # of times to update the net (training iterations) # Solve using the stochastic gradient descent (SGD) algorithm. # Other choices include 'Adam' and 'RMSProp'. s.type = 'SGD' # Set the initial learning rate for SGD. s.base_lr = base_lr # Set `lr_policy` to define how the learning rate changes during training. # Here, we 'step' the learning rate by multiplying it by a factor `gamma` # every `stepsize` iterations. s.lr_policy = 'step' s.gamma = 0.1 s.stepsize = 20000 # Set other SGD hyperparameters. Setting a non-zero `momentum` takes a # weighted average of the current gradient and previous gradients to make # learning more stable. L2 weight decay regularizes learning, to help prevent # the model from overfitting. s.momentum = 0.9 s.weight_decay = 5e-4 # Display the current training loss and accuracy every 1000 iterations. s.display = 1000 # Snapshots are files used to store networks we've trained. Here, we'll # snapshot every 10K iterations -- ten times during training. s.snapshot = 10000 s.snapshot_prefix = caffe_root + 'models/finetune_flickr_style/finetune_flickr_style' # Train on the GPU. Using the CPU to train large networks is very slow. s.solver_mode = caffe_pb2.SolverParameter.GPU # Write the solver to a temporary file and return its filename. with tempfile.NamedTemporaryFile(delete=False) as f: f.write(str(s)) return f.name- 定义
run_solvers函数，输入一个求解器列表（有两个或多个不同的求解器），它以轮询的方式逐个执行并记录精度和损失，最后保存权重。函数返回 精度、损失、权重。
def run_solvers(niter, solvers, disp_interval=10): """Run solvers for niter iterations, returning the loss and accuracy recorded each iteration. `solvers` is a list of (name, solver) tuples.""" blobs = ('loss', 'acc') loss, acc = ({name: np.zeros(niter) for name, _ in solvers} for _ in blobs) for it in range(niter): for name, s in solvers: s.step(1) # run a single SGD step in Caffe loss[name][it], acc[name][it] = (s.net.blobs[b].data.copy() for b in blobs) if it % disp_interval == 0 or it + 1 == niter: loss_disp = '; '.join('%s: loss=%.3f, acc=%2d%%' % (n, loss[n][it], np.round(100*acc[n][it])) for n, _ in solvers) print '%3d) %s' % (it, loss_disp) # Save the learned weights from both nets. weight_dir = tempfile.mkdtemp() weights = {} for name, s in solvers: filename = 'weights.%s.caffemodel' % name weights[name] = os.path.join(weight_dir, filename) s.net.save(weights[name]) return loss, acc, weights- 定义
创建两个求解器，一个
style_solver通过copy_from的方式加载预训练权重，另一个scratch_style_solver采用随机初始化网络，将两个求解器作为列表参数调用run_solvers训练网络。niter = 200 # number of iterations to train # Reset style_solver as before. style_solver_filename = solver(style_net(train=True)) style_solver = caffe.get_solver(style_solver_filename) style_solver.net.copy_from(weights) # For reference, we also create a solver that isn't initialized from # the pretrained ImageNet weights. scratch_style_solver_filename = solver(style_net(train=True)) scratch_style_solver = caffe.get_solver(scratch_style_solver_filename) print 'Running solvers for %d iterations...' % niter solvers = [('pretrained', style_solver), ('scratch', scratch_style_solver)] loss, acc, weights = run_solvers(niter, solvers) print 'Done.' train_loss, scratch_train_loss = loss['pretrained'], loss['scratch'] train_acc, scratch_train_acc = acc['pretrained'], acc['scratch'] style_weights, scratch_style_weights = weights['pretrained'], weights['scratch'] # Delete solvers to save memory. del style_solver, scratch_style_solver, solvers绘制上面保存的两种网络的精度值和损失值的对比图
plot(np.vstack([train_loss, scratch_train_loss]).T) xlabel('Iteration #') ylabel('Loss')定义一个评估函数
eval_style_net，通过构建一个新的TEST网络来测试上面训练迭代好的权重参数，看一下网络的平均精度。def eval_style_net(weights, test_iters=10): test_net = caffe.Net(style_net(train=False), weights, caffe.TEST) accuracy = 0 for it in xrange(test_iters): accuracy += test_net.forward()['acc'] accuracy /= test_iters return test_net, accuracytest_net, accuracy = eval_style_net(style_weights) print 'Accuracy, trained from ImageNet initialization: %3.1f%%' % (100*accuracy, ) scratch_test_net, scratch_accuracy = eval_style_net(scratch_style_weights) print 'Accuracy, trained from random initialization: %3.1f%%' % (100*scratch_accuracy, )
4. 端到端微调
将
style_net的参数设置为learn_all=True来训练所有的层（默认情况是learn_all=False冻结FC1到FC7层）end_to_end_net = style_net(train=True, learn_all=True) # Set base_lr to 1e-3, the same as last time when learning only the classifier. # You may want to play around with different values of this or other # optimization parameters when fine-tuning. For example, if learning diverges # (e.g., the loss gets very large or goes to infinity/NaN), you should try # decreasing base_lr (e.g., to 1e-4, then 1e-5, etc., until you find a value # for which learning does not diverge). base_lr = 0.001 style_solver_filename = solver(end_to_end_net, base_lr=base_lr) style_solver = caffe.get_solver(style_solver_filename) style_solver.net.copy_from(style_weights) scratch_style_solver_filename = solver(end_to_end_net, base_lr=base_lr) scratch_style_solver = caffe.get_solver(scratch_style_solver_filename) scratch_style_solver.net.copy_from(scratch_style_weights) print 'Running solvers for %d iterations...' % niter solvers = [('pretrained, end-to-end', style_solver), ('scratch, end-to-end', scratch_style_solver)] _, _, finetuned_weights = run_solvers(niter, solvers) print 'Done.' style_weights_ft = finetuned_weights['pretrained, end-to-end'] scratch_style_weights_ft = finetuned_weights['scratch, end-to-end'] # Delete solvers to save memory. del style_solver, scratch_style_solver, solvers端到端训练完之后，调用上面定义的评估函数
eval_style_net看一下网络的平均精度test_net, accuracy = eval_style_net(style_weights_ft) print 'Accuracy, finetuned from ImageNet initialization: %3.1f%%' % (100*accuracy, ) scratch_test_net, scratch_accuracy = eval_style_net(scratch_style_weights_ft) print 'Accuracy, finetuned from random initialization: %3.1f%%' % (100*scratch_accuracy, )拿最前面用来测试的那张图片来看一下端到端训练的网络的top5精度
plt.imshow(deprocess_net_image(image)) disp_style_preds(test_net, image)最后在测试网络
test_net的batch中（测试集）挑一张图片显示并输出top5batch_index = 1 image = test_net.blobs['data'].data[batch_index] plt.imshow(deprocess_net_image(image)) # 显示挑出来的图片 print 'actual label =', style_labels[int(test_net.blobs['label'].data[batch_index])]disp_style_preds(test_net, image) # 输出图片对应的Top5disp_imagenet_preds(imagenet_net, image) # 拿完成没有改动ImageNet模型的输出做一个对比
1503
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
