Re: Predicting an object over an pretrained model is not working
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. Because the image only shows that, and that a train and a sheep wont have any target position or any probability whatsoever in the image weirdobject.jpg On Wed, 31 Jul 2024, 00:19 dn via Python-list, wrote: > On 31/07/24 06:18, marc nicole via Python-list wrote: > > Hello all, > > > > I want to predict an object by given as input an image and want to have > my > > model be able to predict the label. I have trained a model using > tensorflow > > based on annotated database where the target object to predict was added > to > > the pretrained model. the code I am using is the following where I set > the > > target object image as input and want to have the prediction output: > > ... > > > > WHile I expect only the dict to contain the small_ball key > > > How's that is possible? where's the prediction output?How to fix the > code? > > > To save us lots of reading and study to be able to help you, please advise: > > 1 what are the meanings of all these numbers? > > > 'sheep': [[233.0, 92.0, 448.0, -103.0, > >> 5.3531270027160645], [167.0, 509.0, 209.0, 101.0, 4.947688579559326], > >> [0.0, 0.0, 448.0, 431.0, 3.393721580505371]] > > 2 (assuming it hasn't) why the dict has not been sorted into a > meaningful order > > 3 how can one tell that the image is more likely to be a sheep than a > train? > > -- > Regards, > =dn > -- > https://mail.python.org/mailman/listinfo/python-list > -- https://mail.python.org/mailman/listinfo/python-list
Re: Predicting an object over an pretrained model is not working
On 2024-07-31, marc nicole via Python-list 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
Re: Predicting an object over an pretrained model is not working
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 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 > -- https://mail.python.org/mailman/listinfo/python-list
