Detailed description

If you don't have a background with RCNN, check out the introduction here.

Step1: Training AlexNet using data flower17

Define the model using tflearn API

def create_alexnet(num_classes):
    # Building 'AlexNet'
    network = input_data(shape=[None, 224, 224, 3])
    network = conv_2d(network, 96, 11, strides=4, activation='relu')
    network = max_pool_2d(network, 3, strides=2)
    network = local_response_normalization(network)
    network = conv_2d(network, 256, 5, activation='relu')
    network = max_pool_2d(network, 3, strides=2)
    network = local_response_normalization(network)
    network = conv_2d(network, 384, 3, activation='relu')
    network = conv_2d(network, 384, 3, activation='relu')
    network = conv_2d(network, 256, 3, activation='relu')
    network = max_pool_2d(network, 3, strides=2)
    network = local_response_normalization(network)
    network = fully_connected(network, 4096, activation='tanh')
    network = dropout(network, 0.5)
    network = fully_connected(network, 4096, activation='tanh')
    network = dropout(network, 0.5)
    network = fully_connected(network, num_classes, activation='softmax')
    network = regression(network, optimizer='momentum',
                         loss='categorical_crossentropy',
                         learning_rate=0.001)
    return network

def train(network, X, Y):
    # Training
    model = tflearn.DNN(network, checkpoint_path='model_alexnet',
                        max_checkpoints=1, tensorboard_verbose=2, tensorboard_dir='output')

If you already have a trained model, load the model

    if os.path.isfile('model_save.model'):
        model.load('model_save.model')

Train the model and save as "model_save.model"

    model.fit(X, Y, n_epoch=100, validation_set=0.1, shuffle=True,
              show_metric=True, batch_size=64, snapshot_step=200,
              snapshot_epoch=False, run_id='alexnet_oxflowers17') # epoch = 1000
    # Save the model
    model.save('model_save.model')

Step2: selective search

Here we use the selectivesearch python API so we focus on realizing IOU (interection or union).

def if_intersection(xmin_a, xmax_a, ymin_a, ymax_a, xmin_b, xmax_b, ymin_b, ymax_b):
    if_intersect = False

If no overlap, the region might be background

if xmin_a < xmax_b <= xmax_a and (ymin_a < ymax_b <= ymax_a or ymin_a <= ymin_b < ymax_a):
        if_intersect = True
    elif xmin_a <= xmin_b < xmax_a and (ymin_a < ymax_b <= ymax_a or ymin_a <= ymin_b < ymax_a):
        if_intersect = True
    elif xmin_b < xmax_a <= xmax_b and (ymin_b < ymax_a <= ymax_b or ymin_b <= ymin_a < ymax_b):
        if_intersect = True
    elif xmin_b <= xmin_a < xmax_b and (ymin_b < ymax_a <= ymax_b or ymin_b <= ymin_a < ymax_b):
        if_intersect = True
    else:
        return False

Get the interection area

    if if_intersect == True:
        x_sorted_list = sorted([xmin_a, xmax_a, xmin_b, xmax_b])
        y_sorted_list = sorted([ymin_a, ymax_a, ymin_b, ymax_b])
        x_intersect_w = x_sorted_list[2] - x_sorted_list[1] 
        y_intersect_h = y_sorted_list[2] - y_sorted_list[1]
        area_inter = x_intersect_w * y_intersect_h
        return area_inter

Then we could count the IOU

def IOU(ver1, vertice2):
    # vertices in four points
    vertice1 = [ver1[0], ver1[1], ver1[0]+ver1[2], ver1[1]+ver1[3]]
    area_inter = if_intersection(vertice1[0], vertice1[2], vertice1[1], vertice1[3], vertice2[0], vertice2[2], vertice2[1], vertice2[3])
    if area_inter:
        area_1 = ver1[2] * ver1[3] 
        area_2 = vertice2[4] * vertice2[5] 
        iou = float(area_inter) / (area_1 + area_2 - area_inter)
        return iou
    return False

Step3: Fine tune AlexNet

• IOU: threthold 0.5
• Training SVM: threthold 0.3

Define the fine tune model and check if already trained. Here the "network" argument in tflearn.DNN is same as previous mentioned (AlexNet).

def fine_tune_Alexnet(network, X, Y):
    # Training
    model = tflearn.DNN(network, checkpoint_path='rcnn_model_alexnet',
                        max_checkpoints=1, tensorboard_verbose=2, tensorboard_dir='output_RCNN')
    if os.path.isfile('fine_tune_model_save.model'):
    print("Loading the fine tuned model")
        model.load('fine_tune_model_save.model')
    elif os.path.isfile('model_save.model'):
    print("Loading the alexnet")
    model.load('model_save.model')
    else:
    print("No file to load, error")
        return False
    model.fit(X, Y, n_epoch=10, validation_set=0.1, shuffle=True,
              show_metric=True, batch_size=64, snapshot_step=200,
              snapshot_epoch=False, run_id='alexnet_rcnnflowers2') # epoch = 1000

Train and save as "fine_tune_model_save.model"

# Save the model
    model.save('fine_tune_model_save.model')

Read the last layer of AlexNet and tarin SVM