# DeepStream input preprocessing **URL:** \ **Category:** DeepStream SDK\ **Created:** [July 15, 2022, 9:42am UTC](https://forums.developer.nvidia.com/t/deepstream-input-preprocessing/220897 "2022-07-15T09:42:35Z")\ **Posts on this page:** 8\ **Page:** 1
**Author:** ![peeranat85](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@peeranat85](https://forums.developer.nvidia.com/u/peeranat85)\ **Post date:** [July 15, 2022, 9:42am UTC](https://forums.developer.nvidia.com/t/deepstream-input-preprocessing/220897/1 "2022-07-15T09:42:35Z")
Given an image of size 600x800 (height x width) ![people1](https://global.discourse-cdn.com/nvidia/original/3X/6/2/62c25357196fc6699c6d736c6d5b12f27898c33c.jpeg) The following configs Streammux ```auto enable-padding=1 ``` PGIE ```auto symmetric-padding=1 maintain-aspect-ratio=1 scaling-filter=0 ``` and network input shape 608 x 1088 (height x width) will result in the following image (ignore color channel for now) ![out_0](https://global.discourse-cdn.com/nvidia/original/3X/8/c/8cc564ba205c497846168f11d35533507d312d30.jpeg) This basically resizes and pads the input image and put it in the middle of a black image of size 608 x 1088. From my understanding, this DeepStream config is similar to the following Python code? ```auto def letterbox(img, height=608, width=1088, color=(0, 0, 0)): # resize a rectangular image to a padded rectangular shape = img.shape[:2] # shape = [height, width] ratio = min(float(height)/shape[0], float(width)/shape[1]) new_shape = (round(shape[1] * ratio), round(shape[0] * ratio)) # new_shape = [width, height] dw = (width - new_shape[0]) / 2 # width padding dh = (height - new_shape[1]) / 2 # height padding top, bottom = round(dh - 0.1), round(dh + 0.1) left, right = round(dw - 0.1), round(dw + 0.1) img = cv2.resize(img, new_shape, interpolation=cv2.INTER_AREA) # resized, no border img = cv2.copyMakeBorder(img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color) # padded rectangular return img, ratio, dw, dh ``` Here’s my question 1. Does the Python implementation above match the DeepStream preprocessing? I need to know this because I’d have to rescale the predictions back to the original image input of size 600 x800 with ```auto float net_width = 1088.f, net_height = 608.f; float img_width = 800.f, img_height = 600.f; float gain = min(net_width / img_width, net_height / img_height); float pad_x = (net_width - img_width * gain) / 2; float pad_y = (net_height - img_height * gain) / 2; float x1 = (rect.x - pad_x) / gain; float y1 = (rect.y - pad_y) / gain; float x2 = (rect.x + rect.width - pad_x) / gain; float y2 = (rect.y + rect.height - pad_y) / gain; float width = x2 - x1; float height = y2 - y1; ``` If it’s not the same, can you point to the example of rescaling the predictions back to its original scale. 1. In DeepStream, with currently supported Streammux and PGIE configs, is it possible to pad and not put the resized image in the middle but the top left as below? ![image](https://global.discourse-cdn.com/nvidia/original/3X/a/d/ad5bf5349c9aa09bb1eabe647ddbe031c6de3853.jpeg) **Environment** Architecture: x86\_64 GPU: _NVIDIA GeForce GTX 1650 Ti with Max-Q Design_ NVIDIA GPU Driver: Driver Version: 495.29.05 DeepStream Version: 6.0 (running on docker image [nvcr.io/nvidia/deepstream:6.0-devel](http://nvcr.io/nvidia/deepstream:6.0-devel)) TensorRT Version: _v8001_ Issue Type: Question Thanks Peeranat F. ---
**Author:** ![yuweiw](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/yuweiw/32/101255_2.png) [@yuweiw](https://forums.developer.nvidia.com/u/yuweiw)\ **Post date:** [July 18, 2022, 3:17am UTC](https://forums.developer.nvidia.com/t/deepstream-input-preprocessing/220897/3 "2022-07-18T03:17:19Z")
Hi @peeranat85 , when you set enable-padding, it will preserve the input aspect ratio while scaling by padding with black bands. So when you want to rescale back, you can try to use the gstnvvideoconver plugin, but you should calculate the crop coordinates. ---
**Author:** ![peeranat85](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@peeranat85](https://forums.developer.nvidia.com/u/peeranat85)\ **Post date:** [July 18, 2022, 7:24am UTC](https://forums.developer.nvidia.com/t/deepstream-input-preprocessing/220897/4 "2022-07-18T07:24:10Z")
> So when you want to rescale back, you can try to use the gstnvvideoconver plugin, but you should calculate the crop coordinates. Can you point to any example? I need to know how it is rescaled. ---
**Author:** ![peeranat85](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@peeranat85](https://forums.developer.nvidia.com/u/peeranat85)\ **Post date:** [July 19, 2022, 3:37pm UTC](https://forums.developer.nvidia.com/t/deepstream-input-preprocessing/220897/5 "2022-07-19T15:37:24Z")
Hi @yuweiw May I ask for an update on this? ---
**Author:** ![yuweiw](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/yuweiw/32/101255_2.png) [@yuweiw](https://forums.developer.nvidia.com/u/yuweiw)\ **Post date:** [July 20, 2022, 5:19am UTC](https://forums.developer.nvidia.com/t/deepstream-input-preprocessing/220897/6 "2022-07-20T05:19:13Z")
Hi @peeranat85 , cause you didn’t scale the origin picture. You just add the black bands around the picture.So, I think you can calculate the coordinates of each point from the 608x1088 picture. Then you can use the gstnvvideoconver plugin and set the crop parameters. Could you try this way? Thanks [https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS\_plugin\_gst-nvvideoconvert.html](https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_plugin_gst-nvvideoconvert.html) ---
**Author:** ![peeranat85](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@peeranat85](https://forums.developer.nvidia.com/u/peeranat85)\ **Post date:** [July 20, 2022, 7:37am UTC](https://forums.developer.nvidia.com/t/deepstream-input-preprocessing/220897/7 "2022-07-20T07:37:09Z")
@yuweiw Please, see my response below. > So, I think you can calculate the coordinates of each point from the 608x1088 picture. How can I calculate the coordinates from 608x1088 image back to its original 600x800 image? I couldn’t find any example that shows how. Given the Streammux config ```auto [streammux] gpu-id=0 batch-size=1 # Muxer batch formation timeout, for e.g. 40 millisec. Should ideally be set # based on the fastest source's framerate. batched-push-timeout=40000 # Set muxer output width and height width=1088 height=608 # enable-padding=1, to preserve the input aspect ratio while scaling by padding with black bands. enable-padding=1 ``` the image is padded to the center. From my understanding, it matches the `letterbox` function I wrote earlier? If my understanding is right, then I can use the logic shown in my Question 1 in the main thread. Btw, I wanted the way to rescale the coordinates output by DeepStream back to its original size (600x400), not by manually setting the crop properties as in the `gstnvvideoconvert` plugin. This is because the rescaled coordinates will be saved into a file and it will be compared with plain Pytorch code for in-depth performance evaluation. Thanks ---
**Author:** ![yuweiw](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/yuweiw/32/101255_2.png) [@yuweiw](https://forums.developer.nvidia.com/u/yuweiw)\ **Post date:** [July 20, 2022, 10:55am UTC](https://forums.developer.nvidia.com/t/deepstream-input-preprocessing/220897/8 "2022-07-20T10:55:24Z")
Hi @peeranat85 , yes, it’s similar to your letter\_box code. Cause we have added the black bands to picture. It’s hard to rescale back if you don’t want to crop. Cause we have not integrated the black edge detection and crop algorithm. So if you want to rescale back, you have to use the `gstnvvideoconvert` plugin to crop. We don’t have a simalar example yet. Also, you can try to set the`enable-padding=0`, it maybe easy to rescale back by yourself. ---
**Author:** ![system](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/system/32/68080_2.png) [@system](https://forums.developer.nvidia.com/u/system)\ **Post date:** [August 3, 2022, 10:56am UTC](https://forums.developer.nvidia.com/t/deepstream-input-preprocessing/220897/9 "2022-08-03T10:56:05Z")
Closed on August 3, 2022, 10:56am UTC This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.