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:


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:

第十一期 fNIRS Journal Club 通知 2020/8/29,10am

北京时间2020年8月29日周六上午10点, 深圳大学成晓君助理教授将为大家讲解她去年发表的一篇用近红外超扫描揭示人际协调的神经机制的文章。同时,她还会和大家介绍如何用Granger causality分析两个信号的因果关系。欢迎大家参加并参与讨论。 她要讲的文献如下: Cheng, Pan, Hu, Hu (2019) Coordination Elicits Synchronous Brain Activity Between Co-actors: Frequency Ratio Matters Frontiers in neuroscience 13() 1071 Abstract: People...
Xu Cui
48 sec read

第十期 fNIRS Journal Club 视频

在2020/7/25日, 北京航空航天大学的汪待发副教授讲解了他发表的一篇BCI文章。视频如下: Youtube:https://youtu.be/gAQQrmbWSOcYouku:https://v.youku.com/v_show/id_XNDc2OTAxNzkzMg==.html
Xu Cui
4 sec read

第十期 fNIRS Journal Club 通知 2020/7/25,10am

北京时间2020年7月25日周六上午10点,北京航空航天大学的汪待发副教授,博士生导师,将为大家讲解他们组去年发表的一篇脑机交互(BCI)的近红外文章。欢迎大家参加并参与讨论。 他要讲的文献如下:Y. Zheng,D. Zhang, L. Wang, Y. Wang, H. Deng, S. Zhang, D. Li, D. Wang, “Resting-State-Based Spatial Filtering for an fNIRS-Based Motor Imagery...
Xu Cui
1 min 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 *