mawei/onepilot
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Update README.md

Browse Source 
old-commit-hash: 25c23047603418bf3d852721ee2d172eac052dfd
This commit is contained in:
HaraldSchafer
2021-10-11 15:05:05 -07:00
committed by GitHub
parent 8a7f3c7dbf
commit 0ca698bcf7
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
models/README.md
View File

@@ -5,14 +5,14 @@ To view the architecture of the ONNX networks, you can use [netron](https://netr
### Supercombo input format (Full size: 393738 x float32)
* **image stream**
* Two consecutive images (256 * 512 * 3 in RGB) recorded at 20 Hz : 393216 = 2 * 6 * 128 * 256
* Each 256 * 512 image is represented in YUV with 6 channels : 6 * 128 * 256
* Each 256 * 512 image is represented in YUV420 with 6 channels : 6 * 128 * 256
* Channels 0,1,2,3 represent the full-res Y channel and are represented in numpy as Y[::2, ::2], Y[::2, 1::2], Y[1::2, ::2], and Y[1::2, 1::2]
* Channel 4 represents the half-res U channel
* Channel 4 represents the half-res V channel
* **desire**
* one-shot encoded vector to command model to execute certain actions, bit only needs to be sent for 1 frame : 8
* one-hot encoded vector to command model to execute certain actions, bit only needs to be sent for 1 frame : 8
* **traffic convention**
* one-shot encoded vector to tell model whether traffic is right-hand or left-hand traffic : 2
* one-hot encoded vector to tell model whether traffic is right-hand or left-hand traffic : 2
* **recurrent state**
* The recurrent state vector that is fed back into the GRU for temporal context : 512