Difference between revisions of "PyTorch"

From BITPlan Wiki
Jump to navigation Jump to search
 
(4 intermediate revisions by the same user not shown)
Line 1: Line 1:
 
= Tutorial =
 
= Tutorial =
 
* https://pytorch.org/tutorials/beginner/deep_learning_60min_blitz.html
 
* https://pytorch.org/tutorials/beginner/deep_learning_60min_blitz.html
 +
= Examples =
 +
== MNIST ==
 +
* https://github.com/pytorch/examples/tree/main/mnist
 +
Tried on 2.3 GHz 8 Core Intel Core i9 with no GPU, 16 GB RAM with python 3.10
 +
<source lang='bash' highlight='1'>
 +
date;python main.py --save-model;date
 +
Sa 31 Dez 2022 18:30:38 MST
 +
Train Epoch: 1 [0/60000 (0%)] Loss: 2.305400
 +
Train Epoch: 1 [640/60000 (1%)] Loss: 1.359776
 +
Train Epoch: 1 [1280/60000 (2%)] Loss: 0.842926
 +
Train Epoch: 1 [1920/60000 (3%)] Loss: 0.593794
 +
Train Epoch: 1 [2560/60000 (4%)] Loss: 0.366338
 +
Train Epoch: 1 [3200/60000 (5%)] Loss: 0.469323
 +
Train Epoch: 1 [3840/60000 (6%)] Loss: 0.265342
 +
Train Epoch: 1 [4480/60000 (7%)] Loss: 0.287802
 +
Train Epoch: 1 [5120/60000 (9%)] Loss: 0.584077
 +
Train Epoch: 1 [5760/60000 (10%)] Loss: 0.223495
 +
...
 +
Train Epoch: 14 [57600/60000 (96%)] Loss: 0.036891
 +
Train Epoch: 14 [58240/60000 (97%)] Loss: 0.000181
 +
Train Epoch: 14 [58880/60000 (98%)] Loss: 0.007485
 +
Train Epoch: 14 [59520/60000 (99%)] Loss: 0.000201
 +
 +
Test set: Average loss: 0.0258, Accuracy: 9919/10000 (99%)
 +
 +
Sa 31 Dez 2022 18:45:17 MST
 +
</source>
  
 
= Links =
 
= Links =
 
* https://stackoverflow.com/questions/tagged/pytorch
 
* https://stackoverflow.com/questions/tagged/pytorch
 +
* https://github.com/utkuozbulak/pytorch-cnn-visualizations
 +
* https://github.com/facebookresearch/TorchRay

Latest revision as of 17:47, 3 January 2023

Tutorial

Examples

MNIST

Tried on 2.3 GHz 8 Core Intel Core i9 with no GPU, 16 GB RAM with python 3.10

date;python main.py --save-model;date
Sa 31 Dez 2022 18:30:38 MST
Train Epoch: 1 [0/60000 (0%)]	Loss: 2.305400
Train Epoch: 1 [640/60000 (1%)]	Loss: 1.359776
Train Epoch: 1 [1280/60000 (2%)]	Loss: 0.842926
Train Epoch: 1 [1920/60000 (3%)]	Loss: 0.593794
Train Epoch: 1 [2560/60000 (4%)]	Loss: 0.366338
Train Epoch: 1 [3200/60000 (5%)]	Loss: 0.469323
Train Epoch: 1 [3840/60000 (6%)]	Loss: 0.265342
Train Epoch: 1 [4480/60000 (7%)]	Loss: 0.287802
Train Epoch: 1 [5120/60000 (9%)]	Loss: 0.584077
Train Epoch: 1 [5760/60000 (10%)]	Loss: 0.223495
...
Train Epoch: 14 [57600/60000 (96%)]	Loss: 0.036891
Train Epoch: 14 [58240/60000 (97%)]	Loss: 0.000181
Train Epoch: 14 [58880/60000 (98%)]	Loss: 0.007485
Train Epoch: 14 [59520/60000 (99%)]	Loss: 0.000201

Test set: Average loss: 0.0258, Accuracy: 9919/10000 (99%)

Sa 31 Dez 2022 18:45:17 MST

Links