![Page 1: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/1.jpg)
TensorLayer 2.0Hao Dong
Peking University
1
![Page 2: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/2.jpg)
2
• History of Deep Learning Tools• History of TensorLayer• Future of TensorLayer• Static vs. Dynamic Models• Switching Train/Test Modes• Reuse Weights• Model Information• Customize Layer without Weights• Customize Layer with Weights• Dataflow• Distributed Training
Background
How to Use
How to Use Better
![Page 3: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/3.jpg)
3
• History of Deep Learning Tools• History of TensorLayer• Future of TensorLayer• Static vs. Dynamic Models• Switching Train/Test Modes• Reuse Weights• Model Information• Customize Layer without Weights• Customize Layer with Weights• Dataflow• Distributed Training
Background
How to Use
How to Use Better
![Page 4: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/4.jpg)
4
History of Deep Learning Tools
• Automatic Differentiation
Key reasons for TensorFlow● Largest user base● Widest production adoption● Well-maintained documents● Battlefield-proof quality● TPU !
![Page 5: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/5.jpg)
5
History of Deep Learning Tools
Deep learning high-level elements: neural networks, layers and tensors
http://www.asimovinstitute.org/neural-network-zoo/
Abstraction gap
Low-level interface: dataflow graph, placeholder, session, queue runner, devices …
https://www.tensorflow.org/extend/architecture
Bridged by wrappers: TensorLayer, Keras and TFLearn
• Beyond Automatic Differentiation
![Page 6: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/6.jpg)
6
History of Deep Learning Tools
Theano TensorFlow
Torch Pytorch
Caffe Caffe2
Time
Keras Tflearn TensorLayer
CNTK2016
2010 2015
2017
2014
2016 Sep
2017
2014
2015 2016
2018
![Page 7: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/7.jpg)
7
History of Deep Learning Tools
Theano TensorFlow
Torch Pytorch
Caffe Caffe2
Time
CNTK2016
2010 2015
2017
2014 2017
2002
2018
transfer
transfer
transfermerge
TensorFlow 2.02019
![Page 8: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/8.jpg)
8
• History of Deep Learning Tools• History of TensorLayer• Future of TensorLayer• Static vs. Dynamic Models• Switching Train/Test Modes• Reuse Weights• Model Information• Customize Layer without Weights• Customize Layer with Weights• Dataflow• Distributed Training
Background
How to Use
![Page 9: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/9.jpg)
9
History of TensorLayer
2016 2019
Time
2015 2019
![Page 10: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/10.jpg)
10
History of TensorLayer
10
• TensorLayer 2.0
TensorLayer: A Versatile Library for Efficient Deep Learning Development. H. Dong, A. Supratak et al. ACM MM 2017.
![Page 11: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/11.jpg)
11
History of TensorLayer
GithubDocumentation(English)
![Page 12: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/12.jpg)
12
• History of Deep Learning Tools• History of TensorLayer• Future of TensorLayer• Static vs. Dynamic Models• Switching Train/Test Modes• Reuse Weights• Model Information• Customize Layer without Weights• Customize Layer with Weights• Dataflow• Distributed Training
Background
How to Use
![Page 13: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/13.jpg)
13
Future of TensorLayer
GPU TPU Huawei 晟腾 ShengTeng …
• Platform-agnostic• Research oriented
TensorFlow MindSpore …
![Page 14: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/14.jpg)
14
Future of TensorLayer
Contributors
![Page 15: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/15.jpg)
15
Future of TensorLayer
![Page 16: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/16.jpg)
16
• History of Deep Learning Tools• History of TensorLayer• Future of TensorLayer• Static vs. Dynamic Models• Switching Train/Test Modes• Reuse Weights• Model Information• Customize Layer without Weights• Customize Layer with Weights• Dataflow• Distributed Training
Background
How to Use
![Page 17: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/17.jpg)
17
Static vs. Dynamic ModelsStaticModel
LasagneFashio
n
![Page 18: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/18.jpg)
18
Static vs. Dynamic ModelsDynamicModel
ChainerFashion
![Page 19: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/19.jpg)
19
Static vs. Dynamic Models
StaticModel DynamicModel
ChainerFashionLasagn
eFashion
![Page 20: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/20.jpg)
20
• History of Deep Learning Tools• History of TensorLayer• Future of TensorLayer• Static vs. Dynamic Models• Switching Train/Test Modes• Reuse Weights• Model Information• Customize Layer without Weights• Customize Layer with Weights• Dataflow• Distributed Training
Background
How to Use
![Page 21: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/21.jpg)
21
Switching Train/Test Models
![Page 22: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/22.jpg)
22
• History of Deep Learning Tools• History of TensorLayer• Future of TensorLayer• Static vs. Dynamic Models• Switching Train/Test Modes• Reuse Weights• Model Information• Customize Layer without Weights• Customize Layer with Weights• Dataflow• Distributed Training
Background
How to Use
![Page 23: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/23.jpg)
23
Reuse Weights
ReuseWeightsinStaticModel
![Page 24: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/24.jpg)
24
Reuse Weights
ReuseWeightsinDynamicModel
![Page 25: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/25.jpg)
25
Reuse Weights
ReuseWeightsinStaticModel ReuseWeightsinDynamicModel
![Page 26: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/26.jpg)
26
• History of Deep Learning Tools• History of TensorLayer• Future of TensorLayer• Static vs. Dynamic Models• Switching Train/Test Modes• Reuse Weights• Model Information• Customize Layer without Weights• Customize Layer with Weights• Dataflow• Distributed Training
Background
How to Use
![Page 27: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/27.jpg)
27
Model Information
PrintModelArchitecture
[{'args': {'dtype': tf.float32,'layer_type': 'normal','name': '_inputlayer_1','shape': [None, 784]},
'class': '_InputLayer','prev_layer': None},
{'args': {'keep': 0.8, 'layer_type': 'normal', 'name': 'dropout_1'},'class': 'Dropout','prev_layer': ['_inputlayer_1_node_0']},
{'args': {'act’: ‘relu','layer_type': 'normal','n_units': 800,'name': 'dense_1'},
'class': 'Dense','prev_layer': ['dropout_1_node_0']},
{'args': {'keep': 0.8, 'layer_type': 'normal', 'name': 'dropout_2'},'class': 'Dropout','prev_layer': ['dense_1_node_0']},
{'args': {'act': ‘relu','layer_type': 'normal','n_units': 800,'name': 'dense_2'},
'class': 'Dense','prev_layer': ['dropout_2_node_0']},
{'args': {'keep': 0.8, 'layer_type': 'normal', 'name': 'dropout_3'},'class': 'Dropout','prev_layer': ['dense_2_node_0']},
{'args': {'act’: ‘relu','layer_type': 'normal','n_units': 10,'name': 'dense_3'},
'class': 'Dense','prev_layer': ['dropout_3_node_0']}]
![Page 28: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/28.jpg)
28
Model Information
PrintModelInformation
GetSpecificWeights
SaveWeightsOnly
SaveWeights+ Architecture
.trainable_weights
.nontrainable_weights
![Page 29: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/29.jpg)
29
• History of Deep Learning Tools• History of TensorLayer• Future of TensorLayer• Static vs. Dynamic Models• Switching Train/Test Modes• Reuse Weights• Model Information• Customize Layer without Weights• Customize Layer with Weights• Dataflow• Distributed Training
Background
How to Use
![Page 30: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/30.jpg)
30
Customize Layer without Weights
![Page 31: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/31.jpg)
31
• History of Deep Learning Tools• History of TensorLayer• Future of TensorLayer• Static vs. Dynamic Models• Switching Train/Test Modes• Reuse Weights• Model Information• Customize Layer without Weights• Customize Layer with Weights• Dataflow• Distributed Training
Background
How to Use
![Page 32: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/32.jpg)
32
Customize Layer with Weights
![Page 33: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/33.jpg)
33
Customize Layer with Weights
![Page 34: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/34.jpg)
34
• History of Deep Learning Tools• History of TensorLayer• Future of TensorLayer• Static vs. Dynamic Models• Switching Train/Test Modes• Reuse Weights• Model Information• Customize Layer without Weights• Customize Layer with Weights• Dataflow• Distributed Training
Background
How to Use
![Page 35: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/35.jpg)
35
Dataflow
𝑡𝑖𝑚𝑒ModelTraining
(GPU)DataProcessing
(CPU)GPU Utilization: 70%
ModelTraining(GPU)
DataProcessing(CPU)
GPU Utilization: 50%
• Training without Dataflow
𝑡𝑖𝑚𝑒
Prepareabatchoftrainingdata
Oneiteration GPUIdle
![Page 36: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/36.jpg)
36
Dataflow
𝑡𝑖𝑚𝑒ModelTraining
(GPU)DataProcessing
(CPU)GPU Utilization: 100%
ModelTraining(GPU)
DataProcessing(CPU)
GPU Utilization: 100%
• Training with Dataflow
𝑡𝑖𝑚𝑒
ModelTraining(GPU)
DataProcessing(CPU)
GPU Utilization: 75%
𝑡𝑖𝑚𝑒
![Page 37: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/37.jpg)
37
• History of Deep Learning Tools• History of TensorLayer• Future of TensorLayer• Static vs. Dynamic Models• Switching Train/Test Modes• Reuse Weights• Model Information• Customize Layer without Weights• Customize Layer with Weights• Dataflow• Distributed Training
Background
How to Use
![Page 38: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/38.jpg)
38
Distributed Training
Model part 3Worker 3
Model part 2Worker 2
Model part 1Worker 1
Model Parallelism
Entire ModelWorker 3
Entire ModelWorker 2 Entire ModelWorker 1
Entire ModelWorker 4
Data Parallelism
![Page 39: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/39.jpg)
39
Distributed Training
Worker 1
Parameter Server
Worker 2 Worker 3
Averages gradients
Worker 1
Parameter Server 1
Worker 2 Worker 3
Averages different parts of the gradients
Parameter Server 2
• Distributed Training: Data Parallelism - Parameter Server
![Page 40: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/40.jpg)
Distributed Training
40
Worker 1
Worker 2 Worker 3
Worker 1
Worker 2 Worker 3
Worker 1
Worker 2 Worker 3
Step 1 Step 2
Step 3
• Distributed Training: Data Parallelism - Horovod - All ringreduce
![Page 41: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/41.jpg)
41
Distributed Training
• Distributed Training: Data Parallelism - Horovod - All ringreduce
Model Gradients Averaged GradientsWorker 1
Model Gradients Averaged GradientsWorker 2
Ring-allreduce
Model Gradients Averaged GradientsWorker 3
![Page 42: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/42.jpg)
42
Please install TensorFlow and TensorLayer and make sure this code is runnable
https://github.com/tensorlayer/tensorlayer/blob/master/examples/basic_tutorials/tutorial_mnist_mlp_static.py
![Page 43: Lecture 12 TensorLayer 2.0 50mins - Deep Generative Models · 2021. 4. 29. · TensorLayer2.0. Hao Dong Peking University. 1. 2. •History of Deep Learning Tools •History of TensorLayer](https://reader036.vdocuments.us/reader036/viewer/2022071509/612d3b571ecc515869420f9e/html5/thumbnails/43.jpg)
Thanks
43