Learning deep learning (project 2, image classification)

1 min read

In this class project, I built a network to classify images in the CIFAR-10 dataset. This dataset is freely available.

The dataset contains 60K color images (32×32 pixel) in 10 classes, with 6K images per class.

Here are the classes in the dataset, as well as 10 random images from each:

airplane
automobile
bird
cat
deer
dog
frog
horse
ship
truck

You can imagine it’s not possible to write down all rules to classify them, so we have to write a program which can learn.

The neural network I created contains 2 hidden layers. The first one is a convolutional layer with max pooling. Then drop out 70% of the connections. The second layer is a fully connected layer with 384 neurons.

def conv_net(x, keep_prob):
    """
    Create a convolutional neural network model
    : x: Placeholder tensor that holds image data.
    : keep_prob: Placeholder tensor that hold dropout keep probability.
    : return: Tensor that represents logits
    """
    # TODO: Apply 1, 2, or 3 Convolution and Max Pool layers
    #    Play around with different number of outputs, kernel size and stride
    # Function Definition from Above:
    #    conv2d_maxpool(x_tensor, conv_num_outputs, conv_ksize, conv_strides, pool_ksize, pool_strides)
    model = conv2d_maxpool(x, conv_num_outputs=18, conv_ksize=(4,4), conv_strides=(1,1), pool_ksize=(8,8), pool_strides=(1,1))
    model = tf.nn.dropout(model, keep_prob)

    # TODO: Apply a Flatten Layer
    # Function Definition from Above:
    #   flatten(x_tensor)
    model = flatten(model)

    # TODO: Apply 1, 2, or 3 Fully Connected Layers
    #    Play around with different number of outputs
    # Function Definition from Above:
    #   fully_conn(x_tensor, num_outputs)
    model = fully_conn(model,384)

    model = tf.nn.dropout(model, keep_prob)

    # TODO: Apply an Output Layer
    #    Set this to the number of classes
    # Function Definition from Above:
    #   output(x_tensor, num_outputs)
    model = output(model,10)

    # TODO: return output
    return model

Then I trained this network using Amazon AWS g2.2xlarge instance. This instance has GPU which is much faster for deep learning (than CPU). I did a simple experiment and find GPU is at least 3 times faster than CPU:

if all layers in gpu: 14 seconds to run 4 epochs,
if conv layer in cpu, other gpu, 36 seconds to run 4 epochs

This is apparently a very crude comparison but GPU is definitely much faster than CPU (at least the ones in AWS g2.2xlarge, cost: $0.65/hour)

Eventually I got ~70% accuracy on the test data, much better than random guess (10%). The time to train the model is ~30 minutes.

You can find my entire code at:
https://www.alivelearn.net/deeplearning/dlnd_image_classification_submission2.html

第十六期 fNIRS Journal Club 通知 2021/01/23,1pm

瑞典 Karolinska Institutet的潘亚峰博士将为大家讲解他们最近发布的一篇用超扫描研究教师学生关系的文章。热烈欢迎大家参与讨论。潘博士为了这次报告,需要一大早就起床。因此本次报告的时间比过去要稍晚一点。 时间: 北京时间2021年1月23日周六下午1点地点: https://zoom.com房间号: 815 4986 9861密码: 796475 Pan, Guyon, Borragán, Hu, Peigneux (2020) Interpersonal brain synchronization with instructor compensates for learner’s...
Xu Cui
53 sec read

第十五期 fNIRS Journal Club 视频

北京时间2020年12月27日周日上午10点, 香港中文大学二年级博士生胡玥讲了一篇用神经网络去除运动伪迹的文章。视频如下: Youtube: https://youtu.be/mZkGzm1R7ak Youku: https://v.youku.com/v_show/id_XNTAyODUyMTEyOA==.html
Xu Cui
4 sec read

第十五期 fNIRS Journal Club 通知 2020/12/27,10am

香港中文大学二年级博士生胡玥为大家介绍一篇方法学文献,即基于人工神经网络重構的多通道fNIRS信号运动伪影校正。该方法不仅对心理学,还对运动科学以及康复医学等领域的研究具有重要的参考价值,热烈欢迎大家参与讨论。 时间: 北京时间2020年12月27日周日上午10点地点: https://zoom.com房间号: 859 4100 6556 密码: 467563 Lee, G., Jin, S. H., & An, J. (2018). Motion artifact correction of multi-measured functional...
Xu Cui
51 sec read

2 Replies to “Learning deep learning (project 2, image classification)”

  1. Helpful post. Can you explain your motivation behind using standard deviation on 0.1 while initializing the weights. My network does not learn if i keep the standard deviation to 1. Only when i saw your post and fine tuned my standard deviation to 0.1, it started training. i would like to understand how did you choose the standard deviation of 0.1 🙂

  2. Can you explain how you arrived at the values below?

    model = fully_conn(model,384)
    #model = fully_conn(model,200)
    #model = fully_conn(model,20)

Leave a Reply

Your email address will not be published. Required fields are marked *