Path: ...!fu-berlin.de!uni-berlin.de!not-for-mail
From: Grant Edwards <grant.b.edwards@gmail.com>
Newsgroups: comp.lang.python
Subject: Re: Predicting an object over an pretrained model is not working
Date: Wed, 31 Jul 2024 09:58:12 -0400 (EDT)
Lines: 24
Message-ID: <mailman.53.1722434293.2981.python-list@python.org>
References: <CAGJtH9Qjv2fQm=_HKwhoGS11uh+u4YoTVzYGHF=2jZC9HpdV9A@mail.gmail.com>
 <339c86d5-8cb5-4995-b5ba-12f88d71a107@DancesWithMice.info>
 <CAGJtH9RnQ=bRPs1xh+xo-tj7tMMjfCCNGTe9C0ArvuY_KTFvEg@mail.gmail.com>
 <4WYtwN4HnMznVHX@mail.python.org>
X-Trace: news.uni-berlin.de PnCFY7dG97j3hWbM5NBeCgepiVyp+q4m/Zzu6xL5/Skw==
Cancel-Lock: sha1:qP8IM7TuSgaGyjLAo62zkn3tZVs= sha256:0xVteucgYjzsMr5KSFovK+2gwvU40tTYCHEzCS/Lz0Y=
Return-Path: <grant.b.edwards@gmail.com>
X-Original-To: python-list@python.org
Delivered-To: python-list@mail.python.org
Authentication-Results: mail.python.org; dkim=none reason="no signature";
 dkim-adsp=none (unprotected policy); dkim-atps=neutral
X-Spam-Status: OK 0.034
X-Spam-Evidence: '*H*': 0.93; '*S*': 0.00; 'subject:not': 0.09;
 'train': 0.09; 'that.': 0.15; 'from:addr:grant.b.edwards': 0.16;
 'from:name:grant edwards': 0.16; 'networks,': 0.16; 'neural':
 0.16; 'recognition.': 0.16; 'sheep': 0.16; 'subject:model': 0.16;
 'subject:working': 0.16; 'wrote:': 0.16; 'grant': 0.17;
 'probably': 0.17; 'to:addr:python-list': 0.20; 'machine': 0.22;
 'depends': 0.25; 'classes': 0.26; 'object': 0.26; 'header:User-
 Agent:1': 0.30; 'learning,': 0.31; 'python-list': 0.32; 'but':
 0.32; 'work.': 0.34; 'trying': 0.35; 'meaning': 0.35;
 'from:addr:gmail.com': 0.35; 'target': 0.36; 'those': 0.36; 'use':
 0.39; 'recognition': 0.40; 'should': 0.40; 'probability': 0.64;
 'well': 0.65; 'numbers': 0.67; 'shows': 0.67; 'that,': 0.67;
 'message-id:invalid': 0.68; 'tools': 0.74; 'position': 0.81;
 'subject:over': 0.84
User-Agent: slrn/1.0.3 (Linux)
X-BeenThere: python-list@python.org
X-Mailman-Version: 2.1.39
Precedence: list
List-Id: General discussion list for the Python programming language
 <python-list.python.org>
List-Unsubscribe: <https://mail.python.org/mailman/options/python-list>,
 <mailto:python-list-request@python.org?subject=unsubscribe>
List-Archive: <https://mail.python.org/pipermail/python-list/>
List-Post: <mailto:python-list@python.org>
List-Help: <mailto:python-list-request@python.org?subject=help>
List-Subscribe: <https://mail.python.org/mailman/listinfo/python-list>,
 <mailto:python-list-request@python.org?subject=subscribe>
X-Mailman-Original-Message-ID: <4WYtwN4HnMznVHX@mail.python.org>
X-Mailman-Original-References: <CAGJtH9Qjv2fQm=_HKwhoGS11uh+u4YoTVzYGHF=2jZC9HpdV9A@mail.gmail.com>
 <339c86d5-8cb5-4995-b5ba-12f88d71a107@DancesWithMice.info>
 <CAGJtH9RnQ=bRPs1xh+xo-tj7tMMjfCCNGTe9C0ArvuY_KTFvEg@mail.gmail.com>
Bytes: 3770

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