Setting up basic structure for CIFAR directory.#1554
Merged
danpovey merged 18 commits intokaldi-asr:kaldi_52from Apr 21, 2017
Merged
Setting up basic structure for CIFAR directory.#1554danpovey merged 18 commits intokaldi-asr:kaldi_52from
danpovey merged 18 commits intokaldi-asr:kaldi_52from
Conversation
…tile of value and derivative instead of mean+-stddev (kaldi-asr#1472)
Setting starting point
Contributor
|
OK. So for a CIFAR image which is |
Contributor
Author
|
No I want 32 x 96, where the row-index (0...31) corresponds to the x
position, and the '96' corresponds to the combination of y position and
color (with the color varying fastest).
…On Mon, Apr 17, 2017 at 4:32 PM, Hossein Hadian ***@***.***> wrote:
OK. So for a CIFAR image which is 32x32 with 3 image channels red, green,
and blue you want the feature matrix to be of size 96x32 where for e.g.
the pixel at row i and col j of the red channel of the image is stored at
index (i*3, j) of the feat matrix, and this pixel in the blue channel is
stored at index (i*3+1, j) of the feat matrix, etc. Right?
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub
<#1554 (comment)>, or mute
the thread
<https://github.com/notifications/unsubscribe-auth/ADJVu8j5EIBwC76KmSTXXh8jnEXKVFZjks5rw_Z_gaJpZM4M_kY6>
.
|
Contributor
|
OK, I am going to write the data-prep script in python since I'll have to read binary image data and write Kaldi format matrices (where I'll use the common python lib in steps/libs). Is that fine? |
Contributor
Author
|
Yes, that's fine.
…On Tue, Apr 18, 2017 at 12:04 PM, Hossein Hadian ***@***.***> wrote:
OK, I am going to write the data-prep script in python since I'll have to
read binary image data and write Kaldi format matrices (where I'll use the
common python lib in steps/libs). Is that fine?
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub
<#1554 (comment)>, or mute
the thread
<https://github.com/notifications/unsubscribe-auth/ADJVu_5ATK5P7N6F0NPOGLuYfUVhSbiqks5rxQlHgaJpZM4M_kY6>
.
|
Add batch result
…one is not completing.
Skaiste
pushed a commit
to Skaiste/idlak
that referenced
this pull request
Sep 26, 2018
* [srcipts] steps/nnet3/report/generate_plots.py: plot 5,50,95th percentile of value and derivative instead of mean+-stddev (kaldi-asr#1472) * Update travis.yml so PRs to kaldi_52 are built * Setting up basic structure for CIFAR directory. * [src] Some code changes/additions to support image recognition applications of nnet3 * Adding results for using batchnorm components instead of renorm * Some partial work on CIFAR setup * Removing old results in AMI * More work on nnet3-egs-augment-image.cc * [build] Slight change to how tests are reported, to figure out which one is not completing. * Add data preparation script for CIFAR * Add cmd.sh and run.sh * Various fixes to CIFAR setup * [src] Code fix RE compressed matrices
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
@hhadian, you may want to start your data-preparation script from this branch.
Not sure if I mentioned, I want the filter-dim (==color) to vary the fastest in the columns of the image matrices.