基于caffe2 示例中的MNIST网络(原文(链接在此))，改进用于识别车牌31个汉字，训练用的数据来自上一篇[caffe2 学习笔记03-从图片如何到mdb数据集
原文中,初始参数：
base_r=−0.1 stepsize=1 gamma=0.999定义若干函数：
def AddInput(model, batch_size, db, db_type): #载入数据 # load the data data_uint8, label = model.TensorProtosDBInput( [], ["data_uint8", "label"], batch_size=batch_size, db=db, db_type=db_type) # cast the data to float data = model.Cast(data_uint8, "data", to=core.DataType.FLOAT) # scale data from [0,255] down to [0,1] # data = model.Scale(data, data, scale=float(1./256)) # don't need the gradient for the backward pass data = model.StopGradient(data, data) return data, label def AddLeNetModel(model, data): #设置网络 """ This part is the standard LeNet model: from data to the softmax prediction. For each convolutional layer we specify dim_in - number of input channels and dim_out - number or output channels. Also each Conv and MaxPool layer changes the image size. For example, kernel of size 5 reduces each side of an image by 4. While when we have kernel and stride sizes equal 2 in a MaxPool layer, it divides each side in half. """ # Image size: 28 x 28 -> 24 x 24 conv1 = brew.conv(model, data, 'conv1', dim_in=3, dim_out=20, kernel=5) # Image size: 24 x 24 -> 12 x 12 pool1 = brew.max_pool(model, conv1, 'pool1', kernel=2, stride=2) # Image size: 12 x 12 -> 8 x 8 conv2 = brew.conv(model, pool1, 'conv2', dim_in=20, dim_out=100, kernel=5) # Image size: 8 x 8 -> 4 x 4 pool2 = brew.max_pool(model, conv2, 'pool2', kernel=2, stride=2) # 50 * 4 * 4 stands for dim_out from previous layer multiplied by the image size fc3 = brew.fc(model, pool2, 'fc3', dim_in=100 * 4 * 4, dim_out=500) #fc3 = brew.relu(model, fc3, fc3) relu = brew.relu(model, fc3, fc3) pred = brew.fc(model, relu, 'pred', 500, 31) softmax = brew.softmax(model, pred, 'softmax') return softmax def AddAccuracy(model, softmax, label): #添加精度记录 """Adds an accuracy op to the model""" accuracy = brew.accuracy(model, [softmax, label], "accuracy") return accuracy def AddTrainingOperators(model, softmax, label): #添加训练操作符 """Adds training operators to the model.""" xent = model.LabelCrossEntropy([softmax, label], 'xent') # compute the expected loss loss = model.AveragedLoss(xent, "loss") # track the accuracy of the model AddAccuracy(model, softmax, label) # use the average loss we just computed to add gradient operators to the model model.AddGradientOperators([loss]) # do a simple stochastic gradient descent ITER = brew.iter(model, "iter") # set the learning rate schedule ############################### 设置学习速率 ############################### LR = model.LearningRate( ITER, "LR", base_lr=-0.0083, policy="step", stepsize=1, gamma=0.999 ) # lr = base_lr * (t ^ gamma) #学习速率的设置非常重要，下边的说明 ############################### 设置学习速率 ############################### # ONE is a constant value that is used in the gradient update. We only need # to create it once, so it is explicitly placed in param_init_net. ONE = model.param_init_net.ConstantFill([], "ONE", shape=[1], value=1.0) # Now, for each parameter, we do the gradient updates. for param in model.params: # Note how we get the gradient of each parameter - ModelHelper keeps # track of that. param_grad = model.param_to_grad[param] # The update is a simple weighted sum: param = param + param_grad * LR model.WeightedSum([param, ONE, param_grad, LR], param) def AddBookkeepingOperators(model): #添加记录符 """This adds a few bookkeeping operators that we can inspect later. These operators do not affect the training procedure: they only collect statistics and prints them to file or to logs. """ # Print basically prints out the content of the blob. to_file=1 routes the # printed output to a file. The file is going to be stored under # root_folder/[blob name] model.Print('accuracy', [], to_file=1) model.Print('loss', [], to_file=1) # Summarizes the parameters. Different from Print, Summarize gives some # statistics of the parameter, such as mean, std, min and max. for param in model.params: model.Summarize(param, [], to_file=1) model.Summarize(model.param_to_grad[param], [], to_file=1) # Now, if we really want to be verbose, we can summarize EVERY blob # that the model produces; it is probably not a good idea, because that # is going to take time - summarization do not come for free. For this # demo, we will only show how to summarize the parameters and their # gradients.开始训练：
before = time.time() localtime = time.localtime(before) print("start at : ", time.asctime(localtime)) # The parameter initialization network only needs to be run once. workspace.RunNetOnce(train_model.param_init_net) # creating the network workspace.CreateNet(train_model.net, overwrite=True) # set the number of iterations and track the accuracy & loss total_iters = 10000 accuracy = np.zeros(total_iters) loss = np.zeros(total_iters) # Now, we will manually run the network for 200 iterations. for i in range(total_iters): # print("iter: ",i) workspace.RunNet(train_model.net) accuracy[i] = workspace.FetchBlob('accuracy') loss[i] = workspace.FetchBlob('loss') after = time.time() # After the execution is done, let's plot the values. print("time in seconds: ", after - before) print("time in minutes: ", (after - before)/60) localtime = time.localtime(after) print("end at : ", time.asctime(localtime)) pyplot.plot(loss, 'b') pyplot.plot(accuracy, 'r') pyplot.legend(('Loss', 'Accuracy'), loc='upper right')输出：
('start at : ', 'Thu Aug 31 13:59:06 2017') ('time in seconds: ', 2490.3361990451813) ('time in minutes: ', 41.50560331741969) ('end at : ', 'Thu Aug 31 14:40:36 2017')正常训练结果如下： 尽管有波动，但是能够看出loss值在逐渐降低，accuracy在逐渐向1贴近，模型有收敛的趋势
不正常的训练结果：
可见，loss并未降低，而是增大，并且呈现周期性，accuracy看不清，但是肯定不是趋近于1的
经过分析，发现 learning rate，batch_size，总训练数据量training set存在如下关系时，训练曲线是较为正常的
batch_sizetraining set∗1learning rate=3.3分析结果：当batch size过小，同时learning rate相对过大时，会让模型进入局部陷阱中震荡，无法跳出局部最优区域，从而呈现出上边第3~4图现象
利用test数据集进行测试，当然，实际应该用validation数据集选择模型，然后用test数据集测试最终选择好的模型结果； 测试代码如下：
before = time.time() localtime = time.localtime(before) print("start at : ", time.asctime(localtime)) workspace.RunNetOnce(test_model.param_init_net) workspace.CreateNet(test_model.net, overwrite=True) test_accuracy = np.zeros(100) for i in range(100): workspace.RunNet(test_model.net.Proto().name) test_accuracy[i] = workspace.FetchBlob('accuracy') # After the execution is done, let's plot the values. pyplot.plot(test_accuracy, 'r') pyplot.title('Acuracy over test batches.') print('test_accuracy: %f' % test_accuracy.mean()) after = time.time() print("time in seconds: ", after - before) print("time in minutes: ", (after - before)/60) localtime = time.localtime(after) print("end at : ", time.asctime(localtime))输出结果：
('start at : ', 'Thu Aug 31 13:55:28 2017') test_accuracy: 0.708770 ('time in seconds: ', 2.4325649738311768) ('time in minutes: ', 0.040542749563852946) ('end at : ', 'Thu Aug 31 13:55:30 2017')