MNIST_identification with CNN

accuracy rate = 99.13%

figure out which is the best suit me

Not Started

tensorflow K-means algorithm implement

MNIST identification with CNN then using K-means to clustering

Still can't understand how to use K-means to build reduce fuction

Rewrite Cifar10 with newest tensorflow API (1.2.0-rc1) and create a pull request to google, hope they will merge my code

#10349

read steps

• tf.Reader
• tf.image
• tf.train.string_input_producer
• tf.get_variable tf.Variable tf.scope
• weight_decay (conceptual)
• weight_decay (coding)

1. tf.truncated_normal
2. tf.l2_loss
3. tf.multiply(step 1, step 2)
4. tf.add_to_collection
5. use collection

• bias_add
• loss_function
• train

is cloth

not cloth

Accuracy: 0.86

Add a drop out layer

Accuracy: 0.91

Fixed a predict problem

Accuracy: 0.93

Figuring out how to optimize

Use Batch normalization to optimize predict Accuracy

Trying to understand

1. gan
2. dc-gan
3. ac-gan( basic-usage )
4. ac-gan with cnn

1. Understanding transfer theory
2. Basic usage
3. Understanding fast style transfer theory
4. Fast Style Transfer usage

1. train_sets download -> me
2. coding -> me
3. make test_sets -> me and teammate
4. train
5. optimize

Failed because of output image is too big and sample sets is not enough

Optimize it in 2 days

[x] stock LSTM prediction use LSTM neural network to predict stock data

[X] VAE

[x] vocal track AutoEncoder

1. V1.0 basic AutoEncoder model
2. V1.1 batch_norm
3. [] Generator