| 3과목 2장 |
다운로드 |
109 |
CUDA Toolkit |
-
|
https://developer.nvidia.com/cuda-downloads
|
| 3과목 2장 |
다운로드 |
110 |
cuDNN |
-
|
https://developer.nvidia.com/cudnn
|
| 4과목 1장 |
코드 |
147-148 |
6-1) Hypothesis using matrix |
[4과목1장] 6-1. Hypothesis using matrix.ipynb
|
-
|
| 4과목 1장 |
코드 |
148-149 |
6-2) matrix |
[4과목1장] 6-2. matrix.ipynb
|
https://github.com/hunkim/DeepLearningZeroToAll/blob/master/lab-04-2-multi_variable_matmul_linear_regression.py
|
| 4과목 1장 |
데이터 |
149-151 |
6-3) Loading data from file |
data-01-test-score.csv
|
https://github.com/hunkim/DeepLearningZeroToAll
|
| 4과목 1장 |
코드 |
149-151 |
6-3) Loading data from file |
[4과목1장] 6-3. Loading data from file.ipynb
|
-
|
| 4과목 1장 |
코드 |
161-162 |
9-1) Logistic (regression) classifier - 실습 |
[4과목1장] 9-1. Logistic (regression) classifier - 실습.ipynb
|
-
|
| 4과목 1장 |
코드 |
170-172 |
12) Softmax classifier |
[4과목1장] 12. Softmax Classifier - 실습.ipynb
|
-
|
| 4과목 1장 |
데이터 |
173 |
13-1) softmax_cross_entropy_with_logits |
data-04-zoo.csv
|
https://github.com/hunkim/DeepLearningZeroToAll
|
| 4과목 1장 |
내용출처 |
173 |
13-2) tf.one_hot and reshape |
-
|
https://www.tensorflow.org/api_docs/python/tf/one_hot
|
| 4과목 1장 |
데이터 |
174 |
13-2) tf.one_hot and reshape |
zoo1.csv
|
https://github.com/droglenc/NCData
|
| 4과목 1장 |
코드 |
172-175 |
13) Softmax Cross entropy with logits - 실습 |
[4과목1장] 13. Softmax Cross entropy with logits - 실습.ipynb
|
-
|
| 4과목 1장 |
코드 |
180-182 |
16) Learning rate, Evaluation - 실습 |
[4과목1장] 16. Learning rate Evaluation - 실습.ipynb
|
https://github.com/hunkim/DeepLearningZeroToAll/blob/master/lab-07-1-learning_rate_and_evaluation.py
|
| 5과목 1장 |
내용출처 |
190 |
2-다) 신경망 모형의 문제 |
-
|
http://cs231n.github.io/convolutional-networks/
|
| 5과목 1장 |
내용출처 |
191 |
2-라) 신경망 모형의 문제를 해결하다 |
-
|
https://devblogs.nvidia.com/inference-next-step-gpu-accelerated-deep-learning/
|
| 5과목 1장 |
내용출처 |
193 |
3-나) Neural networks that can explain photos |
-
|
https://gigaom.com/2014/11/18/google-stanford-build-hybrid-neural-networks-that-can-explain-photos/
|
| 5과목 1장 |
내용출처 |
193 |
4-나) 활용-컴퓨터비전(Computer vision)과 패턴인식(Pattern recognition) |
-
|
https://www.youtube.com/watch?v=6SENw1DoKPQ&feature=youtu.be
|
| 5과목 1장 |
내용출처 |
194 |
4-나) 활용-컴퓨터비전(Computer vision)과 패턴인식(Pattern recognition) |
-
|
http://iizuka.cs.tsukuba.ac.jp/projects/colorization/en/
|
| 5과목 1장 |
내용출처 |
194 |
4-나) 활용-컴퓨터비전(Computer vision)과 패턴인식(Pattern recognition) |
-
|
https://arxiv.org/pdf/1702.00783.pdf?xtor=AL-32280680
|
| 5과목 1장 |
내용출처 |
195 |
4-나) 활용-컴퓨터비전(Computer vision)과 패턴인식(Pattern recognition) |
-
|
https://www.youtube.com/watch?v=pW6nZXeWlGM&feature=youtu.be
|
| 5과목 1장 |
내용출처 |
195 |
4-나) 활용-컴퓨터비전(Computer vision)과 패턴인식(Pattern recognition) |
-
|
https://www.youtube.com/watch?v=xhp47v5OBXQ
|
| 5과목 1장 |
내용출처 |
196 |
4-다) 활용-컴퓨터 게임, 로봇 & 자율자동차 |
-
|
https://youtu.be/V1eYniJ0Rnk
|
| 5과목 1장 |
내용출처 |
196 |
4-다) 활용-컴퓨터 게임, 로봇 & 자율자동차 |
-
|
https://youtu.be/qv6UVOQ0F44
|
| 5과목 1장 |
내용출처 |
196 |
4-다) 활용-컴퓨터 게임, 로봇 & 자율자동차 |
-
|
https://www.youtube.com/watch?v=aKed5FHzDTw&feature=youtu.be
|
| 5과목 1장 |
내용출처 |
197 |
4-다) 활용-컴퓨터 게임, 로봇 & 자율자동차 |
-
|
https://youtu.be/rVlhMGQgDkY
|
| 5과목 1장 |
내용출처 |
197 |
4-라) 활용-소리(sound), 미술(art) |
-
|
https://www.youtube.com/watch?v=j60J1cGINX4&feature=youtu.be
|
| 5과목 2장 |
코드 |
209 |
4-1) 퍼셉트론(OR) - 실습 |
[5과목2장] 4. 퍼셉트론(OR)-실습.ipynb
|
-
|
| 5과목 2장 |
코드 |
210-211 |
5) Neural Nets(NN) for XOR |
[5과목2장] 5. Neural Nets(NN) for XOR.ipynb
|
https://github.com/hunkim/DeepLearningZeroToAll/blob/master/lab-08-tensor_manipulation.ipynb
|
| 5과목 2장 |
코드 |
213-218 |
6) 퍼셉트론(XOR) - 실습1 |
[5과목2장] 6. 퍼셉트론(XOR)-실습1.ipynb
|
-
|
| 5과목 3장 |
코드 |
221 |
1) XOR with NN |
[5과목3장] 1. XOR with NN.ipynb
|
-
|
| 5과목 3장 |
코드 |
225-226 |
2) TensorBoard for XOR NN |
-
|
https://github.com/hunkim/DeepLearningZeroToAll/blob/master/lab-09-4-xor_tensorboard.py
|
| 5과목 3장 |
내용출처 |
226 |
2) TensorBoard for XOR NN |
-
|
http://cs231n.github.io/optimization-2/#staged
|
| 5과목 3장 |
코드 |
236-240 |
5) sigmod 보다 RELU가 더 좋아 |
-
|
-
|
| 6과목 1장 |
내용출처 |
286-288 |
7-1) CNN case study - LeNet-5 |
-
|
https://www.youtube.com/watch?v=EPFQ3z2xIQ8
|
| 6과목 1장 |
내용출처 |
291 |
7-3) CNN case study - ResNet |
-
|
https://www.youtube.com/watch?v=1PGLj-uKT1w
|
| 6과목 1장 |
내용출처 |
294 |
8-2) CNN for CT images |
-
|
https://www.slideshare.net/GYLee3/ss-72966495
|
| 6과목 1장 |
코드 |
294-298 |
8) CNN Basics |
[6과목1장] 8. CNN Basics.ipynb
|
https://github.com/hunkim/DeepLearningZeroToAll/blob/master/lab-11-0-cnn_basics.ipynb
|
| 6과목 1장 |
내용출처 |
298 |
9-1) Simple CNN |
-
|
http://personal.ie.cuhk.edu.hk/~ccloy/project_target_code/index.html
|
| 6과목 1장 |
코드 |
298-300 |
9) MNIST 99% with CNN (1-6) |
[6과목1장] 9. MNIST 99% with CNN (1-6).ipynb
|
https://github.com/hunkim/DeepLearningZeroToAll/blob/master/pytorch/lab-11-1-mnist_cnn.py
|
| 6과목 1장 |
코드 |
301-302 |
9-7) Deep CNN |
-
|
https://github.com/hunkim/DeepLearningZeroToAll/blob/master/pytorch/lab-11-2-mnist_deep_cnn.py
|
| 6과목 2장 |
내용출처 |
318 |
4-1) RNN applications |
-
|
https://github.com/TensorFlowKR/awesome_tensorflow_implementations
|
| 6과목 2장 |
코드 |
321-322 |
6) RNN Basics (2) |
[6과목2장] 6-2. one node 5 (input-dim) in 2 (hidden_size).ipynb
|
https://github.com/hunkim/DeepLearningZeroToAll/blob/master/lab-12-0-rnn_basics.ipynb
|
| 6과목 2장 |
코드 |
322-323 |
6) RNN Basics (3) |
[6과목2장] 6-3. Upfolding to n sequences.ipynb
|
https://github.com/hunkim/DeepLearningZeroToAll/blob/master/lab-12-0-rnn_basics.ipynb
|
| 6과목 2장 |
코드 |
323-324 |
6) RNN Basics (4) |
[6과목2장] 6-4. Batching input.ipynb
|
https://github.com/hunkim/DeepLearningZeroToAll/blob/master/lab-12-0-rnn_basics.ipynb
|
| 6과목 2장 |
코드 |
324-328 |
7) Teach RNN |
[6과목2장] 7. Teach RNN.ipynb
|
https://github.com/hunkim/DeepLearningZeroToAll/blob/master/lab-12-1-hello-rnn.py
|
| 6과목 2장 |
코드 |
328-329 |
8) RNN with long sequences |
[6과목2장] 8. RNN with long sequences.ipynb
|
https://github.com/hunkim/DeepLearningZeroToAll/blob/master/lab-12-2-char-seq-rnn.py
|
| 6과목 2장 |
코드 |
331-335 |
9) RNN with long sequences With Fully Connection layer |
[6과목2장] 9. RNN with long sequences With Fully Connection layer.ipynb
|
https://github.com/hunkim/DeepLearningZeroToAll/blob/master/lab-12-4-rnn_long_char.py
|
| 6과목 2장 |
코드 |
335-336 |
10) RNN with long sequences : Stacked RNN |
[6과목2장] 10. RNN with long sequences (Stacked RNN).ipynb
|
https://github.com/hunkim/DeepLearningZeroToAll/blob/master/lab-12-4-rnn_long_char.py
|
| 6과목 2장 |
코드 |
337 |
10-5) chr/word rnn (char/word level n to n model) |
-
|
https://github.com/sherjilozair/char-rnn-tensorflow
|
| 6과목 2장 |
코드 |
337 |
10-5) chr/word rnn (char/word level n to n model) |
-
|
https://github.com/hunkim/word-rnn-tensorflow
|
| 6과목 2장 |
코드 |
337-338 |
11) RNN with long sequences : Dynamic RNN |
[6과목2장] 11. RNN with long sequences (Dynamic RNN).ipynb
|
https://github.com/hunkim/DeepLearningZeroToAll/blob/master/lab-12-0-rnn_basics.ipynb
|
| 6과목 2장 |
코드 |
339-341 |
12) RNN with time series data(stock) |
[6과목2장] 12. RNN with time series data(stock).ipynb
|
https://github.com/hunkim/DeepLearningZeroToAll/blob/master/lab-12-5-rnn_stock_prediction.py
|
| 6과목 2장 |
데이터 |
339 |
12) RNN with time series data(stock) |
amazon.csv
|
-
|