Article <mailman.50.1722376937.2981.python-list@python.org>

Deutsch English Français Italiano
<mailman.50.1722376937.2981.python-list@python.org>

View for Bookmarking (what is this?)
Look up another Usenet article
Path: ...!3.eu.feeder.erje.net!feeder.erje.net!weretis.net!feeder8.news.weretis.net!fu-berlin.de!uni-berlin.de!not-for-mail
From: Thomas Passin <list1@tompassin.net>
Newsgroups: comp.lang.python
Subject: Re: Predicting an object over an pretrained model is not working
Date: Tue, 30 Jul 2024 17:45:20 -0400
Lines: 278
Message-ID: <mailman.50.1722376937.2981.python-list@python.org>
References: <CAGJtH9Qjv2fQm=_HKwhoGS11uh+u4YoTVzYGHF=2jZC9HpdV9A@mail.gmail.com>
 <263356ef-7ad8-4abc-9940-bd8536ee13eb@tompassin.net>
 <CAGJtH9TnoFa_JJNi=E0oDouKZjq_sfGYmr0WOFOfZtaGcQTyXA@mail.gmail.com>
 <e55832f1-552f-43b8-849f-2a79e77ecbcc@tompassin.net>
Mime-Version: 1.0
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 8bit
Cancel-Lock: sha1:M94y3DkL4R+kdPT8c/uTd0cMD0k= sha256:5qCs96a2vMKE4dAPPu4q6nBmFkmotPe/LM6vfcCbLJs=
User-Agent: Mozilla Thunderbird
Content-Language: en-US
In-Reply-To: <CAGJtH9TnoFa_JJNi=E0oDouKZjq_sfGYmr0WOFOfZtaGcQTyXA@mail.gmail.com>
Precedence: list
Bytes: 20897

On 7/30/2024 4:49 PM, marc nicole wrote:
> OK, but how's the probability of small_ball greater than others? I can't 
> find it anyway, what's its value?

It's your code. I wouldn't know. I suppose it's represented somewhere in 
all those parameters. You need to understand what those function calls 
are returning.  It's documented somewhere, right?

And you really do need to know the probabilities of the competing images 
because otherwise you won't know how confident you can be that the 
identification is a strong one.

> Le mar. 30 juil. 2024 à 21:37, Thomas Passin via Python-list 
> <python-list@python.org <mailto:python-list@python.org>> a écrit :
> 
>     On 7/30/2024 2:18 PM, 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:
>      >
>      >
>      >
>      >
>      >
>      >
>      >
>      >
>      > class MultiObjectDetection():
>      >
>      >      def __init__(self, classes_name):
>      >
>      >          self._classes_name = classes_name
>      >          self._num_classes = len(classes_name)
>      >
>      >          self._common_params = {'image_size': 448, 'num_classes':
>      > self._num_classes,
>      >                  'batch_size':1}
>      >          self._net_params = {'cell_size': 7, 'boxes_per_cell':2,
>      > 'weight_decay': 0.0005}
>      >          self._net = YoloTinyNet(self._common_params,
>     self._net_params,
>      > test=True)
>      >
>      >      def predict_object(self, image):
>      >          predicts = self._net.inference(image)
>      >          return predicts
>      >
>      >      def process_predicts(self, resized_img, predicts, thresh=0.2):
>      >          """
>      >          process the predicts of object detection with one image
>     input.
>      >
>      >          Args:
>      >              resized_img: resized source image.
>      >              predicts: output of the model.
>      >              thresh: thresh of bounding box confidence.
>      >          Return:
>      >              predicts_dict: {"stick": [[x1, y1, x2, y2, scores1],
>     [...]]}.
>      >          """
>      >          cls_num = self._num_classes
>      >          bbx_per_cell = self._net_params["boxes_per_cell"]
>      >          cell_size = self._net_params["cell_size"]
>      >          img_size = self._common_params["image_size"]
>      >          p_classes = predicts[0, :, :, 0:cls_num]
>      >          C = predicts[0, :, :, cls_num:cls_num+bbx_per_cell] # two
>      > bounding boxes in one cell.
>      >          coordinate = predicts[0, :, :, cls_num+bbx_per_cell:] # all
>      > bounding boxes position.
========== REMAINDER OF ARTICLE TRUNCATED ==========