jtthompson1887 · Nov 15, 2022 · Nov 15, 2022 · Nov 15, 2022 · Nov 15, 2022
Showing with 20 additions and 100 deletions.

+15 −19 README.md

+0 −80 environment.yml

+1 −1 posenet/converter/config.py

+4 −0 requirements.txt
diff --git a/README.md b/README.md
@@ -5,27 +5,23 @@ This repository contains a pure Python implementation (multi-pose only) of the G
 I first adapted the JS code more or less verbatim and found the performance was low so made some vectorized numpy/scipy version of a few key functions (named `_fast`).
 
 Further optimization is possible
-* The base MobileNet models have a throughput of 200-300 fps on a GTX 1080 Ti (or better)
-* The multi-pose post processing code brings this rate down significantly. With a fast CPU and a GTX 1080+:
-  * A literal translation of the JS post processing code dropped performance to approx 30fps
-  * My 'fast' post processing results in 90-110fps
-* A Cython or pure C++ port would be even better...  
+
+- The base MobileNet models have a throughput of 200-300 fps on a GTX 1080 Ti (or better)
+- The multi-pose post processing code brings this rate down significantly. With a fast CPU and a GTX 1080+:
+  - A literal translation of the JS post processing code dropped performance to approx 30fps
+  - My 'fast' post processing results in 90-110fps
+- A Cython or pure C++ port would be even better...
 
 ### Install
 
 A suitable Python 3.x environment with a recent version of Tensorflow is required.
 
-Development and testing was done with Conda Python 3.6.8 and Tensorflow 1.12.0 on Linux.
-
-Windows 10 with the latest (as of 2019-01-19) 64-bit Python 3.7 Anaconda installer was also tested.
+Development and testing was done with Python 3.9.13 and Tensorflow 2.10.0 on Linux and Mac OS(Apple Silicon).
 
-If you want to use the webcam demo, a pip version of opencv (`pip install opencv-python`) is required instead of the conda version. Anaconda's default opencv does not include ffpmeg/VideoCapture support. Also, you may have to force install version 3.4.x as 4.x has a broken drawKeypoints binding.
+A environment setup as below should suffice:
 
-A conda environment setup as below should suffice: 
 ```
-conda install tensorflow-gpu scipy pyyaml python=3.6
-pip install opencv-python==3.4.5.20
-
+pip install -r requirements.txt
 ```
 
 ### Usage
@@ -36,7 +32,7 @@ The first time these apps are run (or the library is used) model weights will be
 
 For all demos, the model can be specified with the '--model` argument by using its ordinal id (0-3) or integer depth multiplier (50, 75, 100, 101). The default is the 101 model.
 
-#### image_demo.py 
+#### image_demo.py
 
 Image demo runs inference on an input folder of images and outputs those images with the keypoints and skeleton overlayed.
 
@@ -61,9 +57,9 @@ This port and my work is in no way related to Google.
 The Python conversion code that started me on my way was adapted from the CoreML port at https://github.com/infocom-tpo/PoseNet-CoreML
 
 ### TODO (someday, maybe)
-* More stringent verification of correctness against the original implementation
-* Performance improvements (especially edge loops in 'decode.py')
-* OpenGL rendering/drawing
-* Comment interfaces, tensor dimensions, etc
-* Implement batch inference for image_demo
 
+- More stringent verification of correctness against the original implementation
+- Performance improvements (especially edge loops in 'decode.py')
+- OpenGL rendering/drawing
+- Comment interfaces, tensor dimensions, etc
+- Implement batch inference for image_demo
diff --git a/environment.yml b/environment.yml
diff --git a/posenet/converter/config.py b/posenet/converter/config.py
@@ -6,5 +6,5 @@
 
 def load_config(config_name='config.yaml'):
     cfg_f = open(os.path.join(BASE_DIR, config_name), "r+")
-    cfg = yaml.load(cfg_f)
+    cfg = yaml.safe_load(cfg_f)
     return cfg
diff --git a/requirements.txt b/requirements.txt
@@ -0,0 +1,4 @@
+tensorflow
+scipy
+pyyaml
+opencv-python