I am working on a text recognition problem, in which essentially I am trying to read images similar to captchas.
I implemented a ResNet in keras and I run it on colab with gpu.
Because I cannot upload a million pictures I have created a loop where I train the model in a subset (10000 pics) save them and then load the next subset of pics and continue training.
I did some hyper tuning by trial and error but mostly I am using the original ResNet. My batch size is 128 and epoch = 30.
The model reaches fast a validation accuracy of 14% (after training it to 50k images) but I see no further improvement after this. Theoretically I would expect that the more I train it the more the improvement.
Question 1: What should I do next in order to improve the model accuracy?
Secondly, when I train it. I have some sudden drops in the validation accuracy and I can't understand why this happens.
Finally, most of the times I reach a pick of validation accuracy at the early stage (low number of epoch) and later it goes a bit lower.
Question 2: Why the model behaves like that?
Any ideas around the topic would be very welcome :) Thank you
The code is the following:
Note: I know it is quite a lot, I add it just in case.
load_res_net = False if load_res_net: import keras from keras.layers import Dense, Conv2D, BatchNormalization, Activation from keras.layers import AveragePooling2D, Input, Flatten from keras.optimizers import Adam from keras.callbacks import ModelCheckpoint, LearningRateScheduler from keras.callbacks import ReduceLROnPlateau from keras.preprocessing.image import ImageDataGenerator from keras.regularizers import l2 from keras import backend as K from keras.models import Model from keras.datasets import cifar10 import numpy as np import os # Training parameters batch_size = 32 # orig paper trained all networks with batch_size=128 epochs = 200 num_classes = alphabet.__len__()*10 input_shape = (pic_dim_for_model, pic_dim_for_model, 1) # Subtracting pixel mean improves accuracy subtract_pixel_mean = True n = 3 # Model version # Orig paper: version = 1 (ResNet v1), Improved ResNet: version = 2 (ResNet v2) version = 1 # Computed depth from supplied model parameter n if version == 1: depth = n * 6 + 2 elif version == 2: depth = n * 9 + 2 # Model name, depth and version model_type = 'ResNet%dv%d' % (depth, version) def lr_schedule(epoch): """Learning Rate Schedule Learning rate is scheduled to be reduced after 80, 120, 160, 180 epochs. Called automatically every epoch as part of callbacks during training. # Arguments epoch (int): The number of epochs # Returns lr (float32): learning rate """ lr = 1e-3 if epoch > 180: lr *= 0.5e-3 elif epoch > 160: lr *= 1e-3 elif epoch > 120: lr *= 1e-2 elif epoch > 80: lr *= 1e-1 print('Learning rate: ', lr) return lr def resnet_layer(inputs, num_filters=16, kernel_size=3, strides=1, activation='relu', batch_normalization=True, conv_first=True): """2D Convolution-Batch Normalization-Activation stack builder # Arguments inputs (tensor): input tensor from input image or previous layer num_filters (int): Conv2D number of filters kernel_size (int): Conv2D square kernel dimensions strides (int): Conv2D square stride dimensions activation (string): activation name batch_normalization (bool): whether to include batch normalization conv_first (bool): conv-bn-activation (True) or bn-activation-conv (False) # Returns x (tensor): tensor as input to the next layer """ conv = Conv2D(num_filters, kernel_size=kernel_size, strides=strides, padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(1e-4)) x = inputs if conv_first: x = conv(x) if batch_normalization: x = BatchNormalization()(x) if activation is not None: x = Activation(activation)(x) else: if batch_normalization: x = BatchNormalization()(x) if activation is not None: x = Activation(activation)(x) x = conv(x) return x def resnet_v1(input_shape, depth, num_classes): """ResNet Version 1 Model builder [a] Stacks of 2 x (3 x 3) Conv2D-BN-ReLU Last ReLU is after the shortcut connection. At the beginning of each stage, the feature map size is halved (downsampled) by a convolutional layer with strides=2, while the number of filters is doubled. Within each stage, the layers have the same number filters and the same number of filters. Features maps sizes: stage 0: 32x32, 16 stage 1: 16x16, 32 stage 2: 8x8, 64 The Number of parameters is approx the same as Table 6 of [a]: ResNet20 0.27M ResNet32 0.46M ResNet44 0.66M ResNet56 0.85M ResNet110 1.7M # Arguments input_shape (tensor): shape of input image tensor depth (int): number of core convolutional layers num_classes (int): number of classes (CIFAR10 has 10) # Returns model (Model): Keras model instance """ if (depth - 2) % 6 != 0: raise ValueError('depth should be 6n+2 (eg 20, 32, 44 in [a])') # Start model definition. num_filters = 16 num_res_blocks = int((depth - 2) / 6) inputs = Input(shape=input_shape) x = resnet_layer(inputs=inputs) # Instantiate the stack of residual units for stack in range(3): for res_block in range(num_res_blocks): strides = 1 if stack > 0 and res_block == 0: # first layer but not first stack strides = 2 # downsample y = resnet_layer(inputs=x, num_filters=num_filters, strides=strides) y = resnet_layer(inputs=y, num_filters=num_filters, activation=None) if stack > 0 and res_block == 0: # first layer but not first stack # linear projection residual shortcut connection to match # changed dims x = resnet_layer(inputs=x, num_filters=num_filters, kernel_size=1, strides=strides, activation=None, batch_normalization=False) x = keras.layers.add([x, y]) x = Activation('relu')(x) num_filters *= 2 # Add classifier on top. # v1 does not use BN after last shortcut connection-ReLU x = AveragePooling2D(pool_size=8)(x) y = Flatten()(x) outputs = Dense(num_classes, activation='softmax', kernel_initializer='he_normal')(y) # Instantiate model. model = Model(inputs=inputs, outputs=outputs) return model subtract_pixel_mean = True for tries in range(0,10): data, labels = generate_captchas(number_of_generated_images_to_create = 8000, fonts_path = data_path + '/fonts', lines = 1) data2, labels2 = generate_captchas(number_of_generated_images_to_create = 8000, fonts_path = data_path + '/fonts', lines = 2) data = data + data2 labels = labels + labels2 del data2, labels2 data = np.array(data, dtype="float") / 255.0 labels = np.array(labels) print('try : ' + str(tries)) print('images loaded: ' + str(len(labels))) # Split the training data into separate train and test sets (X_train, X_test, Y_train, Y_test) = train_test_split(data, labels, test_size=0.25, random_state=0) Y_test = np.array([one_hot_encoding_for_word(x) for x in Y_test]) Y_train = np.array([one_hot_encoding_for_word(x) for x in Y_train]) del data # If subtract pixel mean is enabled if subtract_pixel_mean: x_train_mean = np.mean(X_train, axis=0) X_train -= x_train_mean X_test -= x_train_mean # load next part of data, and the model and continue training model.fit(X_train, Y_train, validation_data = (X_test, Y_test), batch_size= 2**7, epochs=40, verbose=2) # Save the trained model to disk model.save(data_path + '/' + name_of_model +'.h5') del X_train, Y_train