experiments/STT-tensorflow
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Update the comment for the normalization parameters

Browse Source 
PiperOrigin-RevId: 312332196
Change-Id: Ief01070eb5f94dd70ffa6a44608fadbcc36a1d30
This commit is contained in:
Lu Wang 2020-05-19 12:40:00 -07:00 committed by TensorFlower Gardener
parent b4360f894c
commit 3754393552
1 changed files with 14 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
tensorflow/lite/experimental/support/metadata/metadata_schema.fbs
View File

@ -317,12 +317,22 @@ table NormalizationOptions{
// mean and std are normalization parameters. Tensor values are normalized // mean and std are normalization parameters. Tensor values are normalized
// on a per-channel basis, by the formula // on a per-channel basis, by the formula
// (x - mean) / std. // (x - mean) / std.
// For example, a float MobileNet model will have
// mean = 127.5f and std = 127.5f.
// A quantized MobileNet model will have
// mean = 0.0f and std = 1.0f.
// If there is only one value in mean or std, we'll propogate the value to // If there is only one value in mean or std, we'll propogate the value to
// all channels. // all channels.
//
// Quantized models share the same normalization parameters as their
// corresponding float models. For example, an image input tensor may have
// the normalization parameter of
// mean = 127.5f and std = 127.5f.
// The image value will be normalized from [0, 255] to [-1, 1].
// Then, for quantized models, the image data should be further quantized
// according to the quantization parameters. In the case of uint8, the image
// data will be scaled back to [0, 255], while for int8, the image data will
// be scaled to [-128, 127].
//
// Both the normalization parameters and quantization parameters can be
// retrieved through the metadata extractor library.
// TODO(b/156644598): add link for the metadata extractor library.
// Per-channel mean of the possible values used in normalization. // Per-channel mean of the possible values used in normalization.
// //