Can ssd mobilenet v1 in object detection tensorflow api be tried with different resize shapes than the default ones?Tensorflow SSD-Mobilenet model accuracy drop after quantization using transform_graphTensorflow object detection on MobileNet, training results oscillateHow to load mobilenet checkpoints into a ssd-mobilenetTensorflow object detection API: output boxes for probability less than 50%Mobilenet SSD Input Image SizeTensorflow Object Detection API no train.py fileHow to configure Tensorflow object detection Android demo to work with Inception v2Weighted softmax at tensorflow object detection API
Does Forgotten Realms setting count as “High magic”?
What does "boys rule, girls drool" mean?
Answer Not A Fool, or Answer A Fool?
Extra initial Aeneid lines in 1662 M. de Marolles version
What is the origin of the "being immortal sucks" trope?
Adding arrowheads to functions?
Test to know when to use GLM over Linear Regression?
How to convert Mn2O3 to Mn3O4?
Teleport everything in a large zone; or teleport all living things and make a lot of equipment disappear
How to make classical firearms effective on space habitats despite the coriolis effect?
What does this line from The Hobbit mean?
Why is the car dealer insisting on a loan instead of cash?
Why does '/' contain '..'?
What is a "major country" as named in Bernie Sanders' Healthcare debate answers?
How to ensure that neurotic or annoying characters don't get tiring on the long run
Output Distinct Factor Cuboids
What is the word for a person who destroys monuments?
Why does JavaScript convert an array of one string to a string, when used as an object key?
How to give my students a straightedge instead of a ruler
Is my sink P-trap too low?
In Bb5 systems against the Sicilian, why does White exchange their b5 bishop without playing a6?
Why are two-stroke engines nearly unheard of in aviation?
geschafft or geschaffen? which one is past participle of schaffen?
Impossible Scrabble Words
Can ssd mobilenet v1 in object detection tensorflow api be tried with different resize shapes than the default ones?
Tensorflow SSD-Mobilenet model accuracy drop after quantization using transform_graphTensorflow object detection on MobileNet, training results oscillateHow to load mobilenet checkpoints into a ssd-mobilenetTensorflow object detection API: output boxes for probability less than 50%Mobilenet SSD Input Image SizeTensorflow Object Detection API no train.py fileHow to configure Tensorflow object detection Android demo to work with Inception v2Weighted softmax at tensorflow object detection API
.everyoneloves__top-leaderboard:empty,.everyoneloves__mid-leaderboard:empty,.everyoneloves__bot-mid-leaderboard:empty margin-bottom:0;
In ssd_mobilenet_v1_coco.config the image_resizer default size is 300x300, or 512x512. State of art results are available for the options only.
But resizing to smaller sizes leads to information loss, can ssd mobilenet be tried with say size 720x720?
Config file:
https://github.com/tensorflow/models/blob/master/research/object_detection/samples/configs/ssd_mobilenet_v1_coco.config
python tensorflow object-detection object-detection-api
asked Mar 28 at 12:53
user10512055user10512055
62 bronze badges
add a comment
|
In ssd_mobilenet_v1_coco.config the image_resizer default size is 300x300, or 512x512. State of art results are available for the options only.
But resizing to smaller sizes leads to information loss, can ssd mobilenet be tried with say size 720x720?
Config file:
https://github.com/tensorflow/models/blob/master/research/object_detection/samples/configs/ssd_mobilenet_v1_coco.config
python tensorflow object-detection object-detection-api
asked Mar 28 at 12:53
user10512055user10512055
62 bronze badges
add a comment
|
In ssd_mobilenet_v1_coco.config the image_resizer default size is 300x300, or 512x512. State of art results are available for the options only.
But resizing to smaller sizes leads to information loss, can ssd mobilenet be tried with say size 720x720?
Config file:
https://github.com/tensorflow/models/blob/master/research/object_detection/samples/configs/ssd_mobilenet_v1_coco.config
python tensorflow object-detection object-detection-api
asked Mar 28 at 12:53
user10512055user10512055
62 bronze badges
In ssd_mobilenet_v1_coco.config the image_resizer default size is 300x300, or 512x512. State of art results are available for the options only.
But resizing to smaller sizes leads to information loss, can ssd mobilenet be tried with say size 720x720?
Config file:
https://github.com/tensorflow/models/blob/master/research/object_detection/samples/configs/ssd_mobilenet_v1_coco.config
python tensorflow object-detection object-detection-api
python tensorflow object-detection object-detection-api
asked Mar 28 at 12:53
user10512055user10512055
62 bronze badges
asked Mar 28 at 12:53
user10512055user10512055
62 bronze badges
asked Mar 28 at 12:53
user10512055user10512055
62 bronze badges
asked Mar 28 at 12:53
user10512055user10512055
62 bronze badges
asked Mar 28 at 12:53
user10512055user10512055
62 bronze badges
62 bronze badges
add a comment
|
add a comment
|
1 Answer
1
active
oldest
votes
It depends whether you're asking about training or inference.
If your goal is to detect objects using a pre-trained model, then it is not recommended to change the resizing parameters, as the model is tuned to work best of these.
However, if you wish to train the model, then yes, you can modify them. However, be aware that changing these values non-marginally would also require you to change the architecture and/or anchor configuration a bit, depending on the objects' sizes you wish to detect. For example, if you're using larger input resolution, than I would recommend adding SSD layers (this is the original configuration, with 6 feature maps with stride of 8, 16, 32, 64, 128 and 256) and changing anchor scales (this is the original, with 6 layers and linear scales in the range of 0.2-0.95 of the image input size).
answered Apr 8 at 13:07
netanel-samnetanel-sam
6422 silver badges11 bronze badges
add a comment
|
Your Answer
StackExchange.ifUsing("editor", function ()
StackExchange.using("externalEditor", function ()
StackExchange.using("snippets", function ()
StackExchange.snippets.init();
);
);
, "code-snippets");
StackExchange.ready(function()
var channelOptions =
tags: "".split(" "),
id: "1"
;
initTagRenderer("".split(" "), "".split(" "), channelOptions);
StackExchange.using("externalEditor", function()
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled)
StackExchange.using("snippets", function()
createEditor();
);
else
createEditor();
);
function createEditor()
StackExchange.prepareEditor(
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: true,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: 10,
bindNavPrevention: true,
postfix: "",
imageUploader:
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/4.0/"u003ecc by-sa 4.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
,
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
);
);
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f55398161%2fcan-ssd-mobilenet-v1-in-object-detection-tensorflow-api-be-tried-with-different%23new-answer', 'question_page');
);
Post as a guest
Required, but never shown
1 Answer
1
active
oldest
votes
1 Answer
1
active
oldest
votes
active
oldest
votes
active
oldest
votes
It depends whether you're asking about training or inference.
If your goal is to detect objects using a pre-trained model, then it is not recommended to change the resizing parameters, as the model is tuned to work best of these.
However, if you wish to train the model, then yes, you can modify them. However, be aware that changing these values non-marginally would also require you to change the architecture and/or anchor configuration a bit, depending on the objects' sizes you wish to detect. For example, if you're using larger input resolution, than I would recommend adding SSD layers (this is the original configuration, with 6 feature maps with stride of 8, 16, 32, 64, 128 and 256) and changing anchor scales (this is the original, with 6 layers and linear scales in the range of 0.2-0.95 of the image input size).
answered Apr 8 at 13:07
netanel-samnetanel-sam
6422 silver badges11 bronze badges
add a comment
|
It depends whether you're asking about training or inference.
If your goal is to detect objects using a pre-trained model, then it is not recommended to change the resizing parameters, as the model is tuned to work best of these.
However, if you wish to train the model, then yes, you can modify them. However, be aware that changing these values non-marginally would also require you to change the architecture and/or anchor configuration a bit, depending on the objects' sizes you wish to detect. For example, if you're using larger input resolution, than I would recommend adding SSD layers (this is the original configuration, with 6 feature maps with stride of 8, 16, 32, 64, 128 and 256) and changing anchor scales (this is the original, with 6 layers and linear scales in the range of 0.2-0.95 of the image input size).
answered Apr 8 at 13:07
netanel-samnetanel-sam
6422 silver badges11 bronze badges
add a comment
|
It depends whether you're asking about training or inference.
If your goal is to detect objects using a pre-trained model, then it is not recommended to change the resizing parameters, as the model is tuned to work best of these.
However, if you wish to train the model, then yes, you can modify them. However, be aware that changing these values non-marginally would also require you to change the architecture and/or anchor configuration a bit, depending on the objects' sizes you wish to detect. For example, if you're using larger input resolution, than I would recommend adding SSD layers (this is the original configuration, with 6 feature maps with stride of 8, 16, 32, 64, 128 and 256) and changing anchor scales (this is the original, with 6 layers and linear scales in the range of 0.2-0.95 of the image input size).
answered Apr 8 at 13:07
netanel-samnetanel-sam
6422 silver badges11 bronze badges
It depends whether you're asking about training or inference.
If your goal is to detect objects using a pre-trained model, then it is not recommended to change the resizing parameters, as the model is tuned to work best of these.
However, if you wish to train the model, then yes, you can modify them. However, be aware that changing these values non-marginally would also require you to change the architecture and/or anchor configuration a bit, depending on the objects' sizes you wish to detect. For example, if you're using larger input resolution, than I would recommend adding SSD layers (this is the original configuration, with 6 feature maps with stride of 8, 16, 32, 64, 128 and 256) and changing anchor scales (this is the original, with 6 layers and linear scales in the range of 0.2-0.95 of the image input size).
answered Apr 8 at 13:07
netanel-samnetanel-sam
6422 silver badges11 bronze badges
answered Apr 8 at 13:07
netanel-samnetanel-sam
6422 silver badges11 bronze badges
answered Apr 8 at 13:07
netanel-samnetanel-sam
6422 silver badges11 bronze badges
answered Apr 8 at 13:07
netanel-samnetanel-sam
6422 silver badges11 bronze badges
6422 silver badges11 bronze badges
add a comment
|
add a comment
|
Got a question that you can’t ask on public Stack Overflow? Learn more about sharing private information with Stack Overflow for Teams.
Got a question that you can’t ask on public Stack Overflow? Learn more about sharing private information with Stack Overflow for Teams.
Thanks for contributing an answer to Stack Overflow!
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
To learn more, see our tips on writing great answers.
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f55398161%2fcan-ssd-mobilenet-v1-in-object-detection-tensorflow-api-be-tried-with-different%23new-answer', 'question_page');
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
