Skip to content

Latest commit

 

History

History
25 lines (19 loc) · 886 Bytes

README.md

File metadata and controls

25 lines (19 loc) · 886 Bytes

HandWritten Digit Recognistion of MNIST Dataset

In this notebook we have understood the image classification task in pytorch.
Tuning the various hyper parameters of the model the accuracy metric was measured.

Model Hyper Parameter

  • Number of Epoch
  • Activation Function (Relu, Leaky_Relu)
  • Optimizer (Adam, SGD)
  • Number of Hidden Layers (1,2,3)
  • Number of Neurons in the Hidden Layer (25,50,100,256)

Results

Parameters Accuracy
15910 93.80%
20175 93.90%
39760 96.00%
40785 96.30%
84060 97.00%
242762 97.40%

Detailed model parameter monitoring sheet