jrobchin / computer-vision-basics-with-python-keras-and-opencv Goto Github PK

I'm working on a project based on your model for gesture recognition and I'm wondering whether you could give me access to your training data. The repository includes only a few examples.

That'd be great help for tweaking your model for my needs, many thanks in advance.

I ran the notebook from the beginning,everything worked fine ,until the "Collecting data"part.
When I ran the "Collecting data" cell, webcam was successfully opened and the hand tracking worked fine after pressing 't' .But when I press 's' ,there was no pics saved in any directory and there was no error or warning reported.

I start a new notebook to just open the webcam and press 's' to save a capture, it worked successfully.
I don't know which part goes wrong here .

Hi, Jason Chin:
In the third last cell in the notebook, there are CURR_POS, which might should be CURR_POSE;
And function get_unique_name appears twice, but I'm confused where it is from.
Thanks for your reply in advance:)

Well I've managed to run through all the steps in notebook, recorded the data, run augmentation script and model isn't predicting gestures properly, I have 4 gestures in my model: number five, number zero (as in sign language), number one (point) and fist. Prediction is very much skewed towards the number five, also it jumps very abruptly between predictions

Oddly enough the training accuracy and validation accuracy are very high

Example bad prediction:

What could be the reason? I followed all steps rigorously, I have around 800 images for training and 100 for validation for each class

Thank you for the tutorial!

Hi, I installed the packages as README.md. But when I import cv2, there is a error.

import cv2

---------------------------------------------------------------------------
ImportError                               Traceback (most recent call last)
<ipython-input-8-c8ec22b3e787> in <module>()
----> 1 import cv2

ImportError: dlopen(/Users/james/anaconda3/envs/cv/lib/python3.5/site-packages/cv2.cpython-35m-darwin.so, 2): Library not loaded: @rpath/libfreetype.6.dylib
  Referenced from: /Users/james/anaconda3/envs/cv/lib/libopencv_freetype.3.4.dylib
  Reason: Incompatible library version: libopencv_freetype.3.4.dylib requires version 22.0.0 or later, but libfreetype.6.dylib provides version 21.0.0

What should I do?