gesture-classifying-model
----------------
To use, first create GestureClassifier object::
>>> predictor = GestureClassifier()
This may take a while as model is being downloaded and loaded (approx. 86 MB of weights).
After creation, you can use the predictor, by passing tensor of frames to transform function.
Numpy array of passed images should have same number of channels, same width and height.
GestureClassifier receives tensor in following shape (None, 64, 64, 3). By that I mean::
>>> input_tensor.shape
>>> (any_num, 64, 64, 3),
where 'any_num' is any number of frames passed. Images should be in range of values 0-255.
You can finally predict probabilities of frame of cropped hands (letters are indexed in order shown below)::
>>> predictor.transform(input_tensor_of images)
Letters order::
'abcdefghiklmnopqrstuvwxy' # alphabetical order for indices from 1 to 24 without letters requiring movement, like 'z' and 'j'
----------------
To use, first create GestureClassifier object::
>>> predictor = GestureClassifier()
This may take a while as model is being downloaded and loaded (approx. 86 MB of weights).
After creation, you can use the predictor, by passing tensor of frames to transform function.
Numpy array of passed images should have same number of channels, same width and height.
GestureClassifier receives tensor in following shape (None, 64, 64, 3). By that I mean::
>>> input_tensor.shape
>>> (any_num, 64, 64, 3),
where 'any_num' is any number of frames passed. Images should be in range of values 0-255.
You can finally predict probabilities of frame of cropped hands (letters are indexed in order shown below)::
>>> predictor.transform(input_tensor_of images)
Letters order::
'abcdefghiklmnopqrstuvwxy' # alphabetical order for indices from 1 to 24 without letters requiring movement, like 'z' and 'j'
1 maintainer
Metadata
1 maintainer
Release files for gesture-classifying-model 0.1.10
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| gesture_classifying_model-0.1.10.tar.gz | 3.2 kB | Details |
Release files / gesture_classifying_model-0.1.10.tar.gz
| Download URL | gesture_classifying_model-0.1.10.tar.gz |
|---|---|
| Size | 3.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
ddbb20dc2f23659b6ca6803167f52d39b2e0c5560621d631557eb33d67873e31
|
|
BLAKE2b-256 checksum How to use checksums |
03f9d415a3012dc53ee2f0eed7fa2eb155f94b95fe8580ad19133099b21c9488
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
