Sujet : Re: Predicting an object over an pretrained model is not working
De : mk1853387 (at) *nospam* gmail.com (marc nicole)
Groupes : comp.lang.pythonDate : 31. Jul 2024, 21:59:58
Autres entêtes
Message-ID : <mailman.54.1722456012.2981.python-list@python.org>
References : 1 2 3 4 5
You invitation to read on machine is not helping, if you wanna enlighten us
on this specific case otherwise pls spare me such comments which i know
On Wed, 31 Jul 2024, 16:00 Grant Edwards via Python-list, <
python-list@python.org> wrote:
On 2024-07-31, marc nicole via Python-list <python-list@python.org> wrote:
>
I suppose the meaning of those numbers comes from this line
predicts_dict[class_name].append([int(xmin), int(ymin), int(xmax),
int(ymax), P[index]]) as well as the yolo inference call. But i was
expecting zeros for all classes except smallball.
>
That's not how machine learning and object recognition works.
>
Because the image only shows that,
>
You know that. The machine doesn't.
>
and that a train and a sheep wont have any target position or any
probability whatsoever in the image weirdobject.jpg
>
That depends on the training data and how the model works.
>
You should probably do some reading on neural networks, machine
learning, and pattern/object recognition. You appear to be trying to
use tools without understanding what they do or how they work.
>
--
Grant
--
https://mail.python.org/mailman/listinfo/python-list
>