cs501r_f2018:lab3
Differences
This shows you the differences between two versions of the page.
| Both sides previous revision Previous revision Next revision | Previous revision | ||
|
cs501r_f2018:lab3 [2018/09/14 17:49] wingated |
cs501r_f2018:lab3 [2018/09/20 15:50] sadler [Detailed specs:] |
||
|---|---|---|---|
| Line 42: | Line 42: | ||
| https://pytorch.org/docs/stable/torch.html#torch.log | https://pytorch.org/docs/stable/torch.html#torch.log | ||
| - | **Part 2:** Implement a few initialization strategies including Xe initialization (sometimes called Xavier), Orthogonal initailization, and uniform random. You can specify which strategy you want to use with a parameter. Helpful links include: | + | **Part 2:** Implement a few initialization strategies which can include Xe initialization (sometimes called Xavier), Orthogonal initailization, and uniform random. You can specify which strategy you want to use with a parameter. Helpful links include: |
| https://hjweide.github.io/orthogonal-initialization-in-convolutional-layers (or the orignal paper: http://arxiv.org/abs/1312.6120) | https://hjweide.github.io/orthogonal-initialization-in-convolutional-layers (or the orignal paper: http://arxiv.org/abs/1312.6120) | ||
| http://andyljones.tumblr.com/post/110998971763/an-explanation-of-xavier-initialization | http://andyljones.tumblr.com/post/110998971763/an-explanation-of-xavier-initialization | ||
| - | **Part 3:** Print the number of parameters in your network and plot accuracy of your training and validation set over time. You should experiment with some deep networks and see if you can't get a network with close to 1,000,000 parameters. | + | **Part 3:** Print the number of parameters in your network and plot accuracy of your training and validation set over time. You should experiment with some deep networks and see if you can get a network with close to 1,000,000 parameters. |
| **Part 4:** Learn about how convolution layers affect the shape of outputs, and answer the following quiz questions. Include these in a new markdown cell in your jupyter notebook. | **Part 4:** Learn about how convolution layers affect the shape of outputs, and answer the following quiz questions. Include these in a new markdown cell in your jupyter notebook. | ||
| Line 56: | Line 56: | ||
| (c=3, h=10, w=10) => (c=22, h=10, w=10) : | (c=3, h=10, w=10) => (c=22, h=10, w=10) : | ||
| - | (c=3, h=10, w=10) => (c=65, h=11, w=11) : | + | (c=3, h=10, w=10) => (c=65, h=12, w=12) : |
| - | (c=3, h=10, w=10) => (c=7, h=15, w=15) : | + | (c=3, h=10, w=10) => (c=7, h=20, w=20) : |
| | | ||
| Using a Kernel size of 5x5: | Using a Kernel size of 5x5: | ||
| Line 72: | Line 72: | ||
| Using Kernel size of 5x3: | Using Kernel size of 5x3: | ||
| - | (c=3, h=10, w=10) => (c=10, h=8, w=8) : (out_channels=10, kernel_size=(5, 5), padding=(1, 0)) | + | (c=3, h=10, w=10) => (c=10, h=8, w=8) : |
| (c=3, h=10, w=10) => (c=100, h=10, w=10) : | (c=3, h=10, w=10) => (c=100, h=10, w=10) : | ||
cs501r_f2018/lab3.txt ยท Last modified: 2021/06/30 23:42 (external edit)
Page Tools
Except where otherwise noted, content on this wiki is licensed under the following license: CC Attribution-Share Alike 4.0 International
