Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix minor typos #562

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Fix minor typos #562

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions chapter08_computer-vision/object-detection.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,7 +56,7 @@
"\n",
"### Default anchor boxes\n",
"\n",
"Since an anchor box can have arbituary shape, \n",
"Since an anchor box can have arbitrary shape, \n",
"we sample a set of anchor boxes as the candidate. \n",
"In particular, for each pixel, we sample multiple boxes \n",
"centered at this pixel but have various sizes and ratios. \n",
Expand Down Expand Up @@ -278,7 +278,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"### Manage preditions from multiple layers\n",
"### Manage predictions from multiple layers\n",
"\n",
"A key property of SSD is that predictions are made \n",
"at multiple layers with shrinking spatial size. \n",
Expand Down Expand Up @@ -878,7 +878,7 @@
"source": [
"### Evaluation metrics\n",
"\n",
"Here, we define two metrics that we'll use to evaluate our performance whien training. \n",
"Here, we define two metrics that we'll use to evaluate our performance when training. \n",
"You're already familiar with accuracy unless you've been naughty and skipped straight to object detection.\n",
"We use the accuracy metric to assess the quality of the class predictions. \n",
"Mean absolute error (MAE) is just the L1 distance, introduced in our [linear algebra chapter](../chapter01_crashcourse/linear-algebra.ipynb).\n",
Expand Down