From 2b84add8706c1e187f28aa26343ced490fda5a8a Mon Sep 17 00:00:00 2001 From: Zhen Ju Date: Mon, 25 Feb 2019 22:01:18 +0800 Subject: [PATCH] Fix typos in inspect_data notebook(feature meap -> feature map) Replace 256*256*3 with 256x256x3, since the '*' won't be displayed in Markdown --- samples/coco/inspect_data.ipynb | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/samples/coco/inspect_data.ipynb b/samples/coco/inspect_data.ipynb index 96b8f17..d897482 100644 --- a/samples/coco/inspect_data.ipynb +++ b/samples/coco/inspect_data.ipynb @@ -541,7 +541,7 @@ "* For each feature map cell, pick any sorting order for the anchors of different ratios. Here we match the order of ratios passed to the function.\n", "\n", "**Anchor Stride:**\n", - "In the FPN architecture, feature maps at the first few layers are high resolution. For example, if the input image is 1024x1024 then the feature meap of the first layer is 256x256, which generates about 200K anchors (256*256*3). These anchors are 32x32 pixels and their stride relative to image pixels is 4 pixels, so there is a lot of overlap. We can reduce the load significantly if we generate anchors for every other cell in the feature map. A stride of 2 will cut the number of anchors by 4, for example. \n", + "In the FPN architecture, feature maps at the first few layers are high resolution. For example, if the input image is 1024x1024 then the feature map of the first layer is 256x256, which generates about 200K anchors (256x256x3). These anchors are 32x32 pixels and their stride relative to image pixels is 4 pixels, so there is a lot of overlap. We can reduce the load significantly if we generate anchors for every other cell in the feature map. A stride of 2 will cut the number of anchors by 4, for example. \n", "\n", "In this implementation we use an anchor stride of 2, which is different from the paper." ]