doc update

diff --git a/docs/det_modelzoo.md b/docs/det_modelzoo.md
index 67493f9e1007390b5328b9e709fae0f238fbc86e..15b0843f891581864e79e082840e5bf886b20e46 100644 (file)
--- a/docs/det_modelzoo.md
+++ b/docs/det_modelzoo.md
@@ -57,11 +57,11 @@ Please see the reference [2] for algorithmic details of the detector.
 <br>
 
 
-- A fixed resolution is indicated by width x height and it means that the inputs are resized to that resolution without preserving the aspect ratio of the image (keep_ratio=False in config files). **A fixed resolution is recommended for embedded inference.** The resolution after resize can be square (example: 512x512) or non-square (example: 768x384). Please note that embedded friendly detectors such as SSD [1] and EfficientDet (arXiv:1911.09070) [3] uses this kind of fixed resizing.<br>
+- A resolution range in the tables is indicated with comma (1536,768) or dash (1536-768) - it means that images are resized to fit within this maximum and minimum size - and the aspect ratio of the original image is preserved (keep_ratio=True in config files). Due to this, each resized image may have a different size depending on the aspect ratio of the original image.
 
-- A resolution range is indicated with comma (1536,768) or dash (1536-768) - it means that images are resized to fit within this maximum and minimum size - but the aspect ratio of the image is preserved (keep_ratio=True in config files). **This means that each image may have a different size after it is resized and hence is not suitable for embedded inference.** For example ONNXRuntime inference software [8] does not allow to do inference with variable size inputs for a given model. 
+- A fixed resolution in the tables is indicated by *width x height* and it means that the inputs are to be resized to that resolution without preserving the aspect ratio of the image (keep_ratio=False in config files). The resolution after resize can be square (example: 512x512) or non-square (example: 768x384).  Detectors such as SSD [1] and EfficientDet (arXiv:1911.09070) [3] uses this kind of fixed resizing. **It is preferable to use this kind of fixed resolution resize for embedded inference** - at least from an accuracy evaluation point of view (where the actual dataset with variable size images may need to be evaluated upon). <br>
 
-- *Mmdetection typically uses a resolution range to train models for most models except SSD. An interesting observation that we had is that such  models trained for non-square resolutions can also be inferred or evaluated using square aspect ratios (with a bit of accuracy drop, of course). This leads to the possibility of reusing the models provided in the [mmdetection model zoo](https://github.com/open-mmlab/mmdetection/blob/master/docs/model_zoo.md) for an embedded scenario.* <br>
+- *Mmdetection typically uses a resolution range to train models for most models except SSD. An interesting observation that we had is that such  models trained for non-square resolutions can also be inferred or evaluated using square aspect ratios (with a bit of accuracy drop, of course). This leads to the possibility of reusing the models provided in the [mmdetection model zoo](https://github.com/open-mmlab/mmdetection/blob/master/docs/model_zoo.md) for fixed resolution inference as well.* <br>
 
 - The models with a \* were not trained by us, but rather taken from mmdetection model zoo and inference is run at the said resolution.<br>