Which is the fastest image pretrained model? Announcing the arrival of Valued Associate #679: Cesar Manara Planned maintenance scheduled April 17/18, 2019 at 00:00UTC (8:00pm US/Eastern) 2019 Moderator Election Q&A - Questionnaire 2019 Community Moderator Election ResultsWhat is the reason behind the minimum image size in the Keras InceptionResNetV2 model?Transfer learning (on pre-trained inception net model) for multi label classification is giving similar probability for all labelsType of images used to train a neural networkPretrained InceptionV3 - very low accuracy on Tobacco datasetThe effect of the image type and the image conversion on deep learning CNN modelIntermediate layer output from pretrained TensorFlow modelImage features (produced by VGG19) do not properly train an ANN in KerasPreprocessing for finetuned CNN model from pretrained modelsDesigning a pretrained DNN for image similarityWhat is the difference between “offline trained model” and “pretrained model”?
Equal values attribute table
Is it true that "carbohydrates are of no use for the basal metabolic need"?
How can I use the Python library networkx from Mathematica?
Why is "Consequences inflicted." not a sentence?
List *all* the tuples!
Using audio cues to encourage good posture
How widely used is the term Treppenwitz? Is it something that most Germans know?
Fundamental Solution of the Pell Equation
What's the purpose of writing one's academic biography in the third person?
Why do people hide their license plates in the EU?
When precisely will security support for Ubuntu GNOME 16.04 LTS end?
2001: A Space Odyssey's use of the song "Daisy Bell" (Bicycle Built for Two); life imitates art or vice-versa?
A binary hook-length formula?
Is it ethical to give a final exam after the professor has quit before teaching the remaining chapters of the course?
How do pianists reach extremely loud dynamics?
Dating a Former Employee
What does an IRS interview request entail when called in to verify expenses for a sole proprietor small business?
Storing hydrofluoric acid before the invention of plastics
How to remove list items depending on predecessor in python
Shortening trees list with (setcdr (nthcdr 2 trees) nil)
Error "illegal generic type for instanceof" when using local classes
Why didn't this character "real die" when they blew their stack out in Altered Carbon?
Why did the rest of the Eastern Bloc not invade Yugoslavia?
How do I stop a creek from eroding my steep embankment?
Which is the fastest image pretrained model?
Announcing the arrival of Valued Associate #679: Cesar Manara
Planned maintenance scheduled April 17/18, 2019 at 00:00UTC (8:00pm US/Eastern)
2019 Moderator Election Q&A - Questionnaire
2019 Community Moderator Election ResultsWhat is the reason behind the minimum image size in the Keras InceptionResNetV2 model?Transfer learning (on pre-trained inception net model) for multi label classification is giving similar probability for all labelsType of images used to train a neural networkPretrained InceptionV3 - very low accuracy on Tobacco datasetThe effect of the image type and the image conversion on deep learning CNN modelIntermediate layer output from pretrained TensorFlow modelImage features (produced by VGG19) do not properly train an ANN in KerasPreprocessing for finetuned CNN model from pretrained modelsDesigning a pretrained DNN for image similarityWhat is the difference between “offline trained model” and “pretrained model”?
$begingroup$
I had been working with pre-trained models and was just curious to know the fastest forward propagating model of all the computer vision pre-trained models. I have been trying to achieve faster processing in one-shot learning and have tried the forward propagation with few models over a single image and the results are as follows:
VGG16: 4.857 seconds
ResNet50: 0.227 seconds
Inception: 0.135 seconds
Can you tell the fastest pre-trained model available out there and the drastic time consumption difference amongst the above-mentioned models.
deep-learning computer-vision transfer-learning inception finetuning
asked Oct 4 '18 at 10:20
thanatozthanatoz
643421
$endgroup$
add a comment |
$begingroup$
I had been working with pre-trained models and was just curious to know the fastest forward propagating model of all the computer vision pre-trained models. I have been trying to achieve faster processing in one-shot learning and have tried the forward propagation with few models over a single image and the results are as follows:
VGG16: 4.857 seconds
ResNet50: 0.227 seconds
Inception: 0.135 seconds
Can you tell the fastest pre-trained model available out there and the drastic time consumption difference amongst the above-mentioned models.
deep-learning computer-vision transfer-learning inception finetuning
asked Oct 4 '18 at 10:20
thanatozthanatoz
643421
$endgroup$
add a comment |
$begingroup$
I had been working with pre-trained models and was just curious to know the fastest forward propagating model of all the computer vision pre-trained models. I have been trying to achieve faster processing in one-shot learning and have tried the forward propagation with few models over a single image and the results are as follows:
VGG16: 4.857 seconds
ResNet50: 0.227 seconds
Inception: 0.135 seconds
Can you tell the fastest pre-trained model available out there and the drastic time consumption difference amongst the above-mentioned models.
deep-learning computer-vision transfer-learning inception finetuning
asked Oct 4 '18 at 10:20
thanatozthanatoz
643421
$endgroup$
I had been working with pre-trained models and was just curious to know the fastest forward propagating model of all the computer vision pre-trained models. I have been trying to achieve faster processing in one-shot learning and have tried the forward propagation with few models over a single image and the results are as follows:
VGG16: 4.857 seconds
ResNet50: 0.227 seconds
Inception: 0.135 seconds
Can you tell the fastest pre-trained model available out there and the drastic time consumption difference amongst the above-mentioned models.
deep-learning computer-vision transfer-learning inception finetuning
deep-learning computer-vision transfer-learning inception finetuning
asked Oct 4 '18 at 10:20
thanatozthanatoz
643421
asked Oct 4 '18 at 10:20
thanatozthanatoz
643421
edited Apr 2 at 5:39
thanatoz
asked Oct 4 '18 at 10:20
thanatozthanatoz
643421
asked Oct 4 '18 at 10:20
thanatozthanatoz
643421
asked Oct 4 '18 at 10:20
thanatozthanatoz
643421
643421
add a comment |
add a comment |
1 Answer
1
active
oldest
votes
$begingroup$
The answer will depend on some things such as your hardware and the image you process. Additional, we should distinguish if you are talking about a single run through the network in training mode or in inference mode. In the former, additional parameters are pre-computed and cached as well as several layers, such as dropout, being used, which are simply left out during inference. I will assume you want to simply produce a single prediction for a single image, so we are talking about inference time.
Factors
The basic correlation will be:
- more parameters (i.e. learnable weights, bigger network) - slower than a model with less parameters
- more recurrent units - slower than a convolutional network, which is slower than a full-connected network1
- complicated activation functions - slower than simple ones, such as ReLU
- deeper networks - slower than shallow networks (with same number of parameters) as less run in parallel on a GPU
Having listed a few factors in the final inference time required (time taken to produce one forward run through the network), I would guess that MobileNetV2 is probably among the fastest pre-trained model (available in Keras). We can see from the following table that this network has a small memory footprint of only 14 megabytes with ~3.5 million parameters. Compare that to your VGG test, with its ~138 million... 40 times more! In addition, the main workhorse layer of MobileNetV2 is a conv layer - they are essentially clever and smaller versions of residual networks.
Extra considerations
The reason I included the whole table above was to highlight that with small memory footprints and fast inference times, comes a cost: low accuracies!
If you compute the ratios of top-5 accuracy versus number of parameters (and generally versus memory), you might find a nice balance between inference time and performance.
1 Have a look at this comparison of CNNs with Recurrent modules
answered Oct 4 '18 at 22:31
n1k31t4n1k31t4
6,5512421
$endgroup$
$begingroup$
It is not as simple as looking at the number of parameters and depth. For instance, ResNet50 is significantly faster than Xception on my hardware, despite having more parameters and a higher depth. Similarly, MobileNet is faster than MovileNetV2 for me. That being said, the mobile nets are effectively built for embedded hardware, and thus less demanding.
$endgroup$
– Wok
Feb 8 at 13:02
$begingroup$
@Wok - You're right, which is why I didn't say that. There are many factors, I gave examples. You would need to do some benchmarking of models on target hardware, given certain data. In a very simplistic approach, the number of parameters is a proxy for number of operations, which is why I chose to include that table and also highlight correlations in memory consumption and model accuracy.
$endgroup$
– n1k31t4
Feb 8 at 13:55
add a comment |
Your Answer
StackExchange.ready(function()
var channelOptions =
tags: "".split(" "),
id: "557"
;
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: false,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: null,
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/3.0/"u003ecc by-sa 3.0 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%2fdatascience.stackexchange.com%2fquestions%2f39177%2fwhich-is-the-fastest-image-pretrained-model%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
$begingroup$
The answer will depend on some things such as your hardware and the image you process. Additional, we should distinguish if you are talking about a single run through the network in training mode or in inference mode. In the former, additional parameters are pre-computed and cached as well as several layers, such as dropout, being used, which are simply left out during inference. I will assume you want to simply produce a single prediction for a single image, so we are talking about inference time.
Factors
The basic correlation will be:
- more parameters (i.e. learnable weights, bigger network) - slower than a model with less parameters
- more recurrent units - slower than a convolutional network, which is slower than a full-connected network1
- complicated activation functions - slower than simple ones, such as ReLU
- deeper networks - slower than shallow networks (with same number of parameters) as less run in parallel on a GPU
Having listed a few factors in the final inference time required (time taken to produce one forward run through the network), I would guess that MobileNetV2 is probably among the fastest pre-trained model (available in Keras). We can see from the following table that this network has a small memory footprint of only 14 megabytes with ~3.5 million parameters. Compare that to your VGG test, with its ~138 million... 40 times more! In addition, the main workhorse layer of MobileNetV2 is a conv layer - they are essentially clever and smaller versions of residual networks.
Extra considerations
The reason I included the whole table above was to highlight that with small memory footprints and fast inference times, comes a cost: low accuracies!
If you compute the ratios of top-5 accuracy versus number of parameters (and generally versus memory), you might find a nice balance between inference time and performance.
1 Have a look at this comparison of CNNs with Recurrent modules
answered Oct 4 '18 at 22:31
n1k31t4n1k31t4
6,5512421
$endgroup$
$begingroup$
It is not as simple as looking at the number of parameters and depth. For instance, ResNet50 is significantly faster than Xception on my hardware, despite having more parameters and a higher depth. Similarly, MobileNet is faster than MovileNetV2 for me. That being said, the mobile nets are effectively built for embedded hardware, and thus less demanding.
$endgroup$
– Wok
Feb 8 at 13:02
$begingroup$
@Wok - You're right, which is why I didn't say that. There are many factors, I gave examples. You would need to do some benchmarking of models on target hardware, given certain data. In a very simplistic approach, the number of parameters is a proxy for number of operations, which is why I chose to include that table and also highlight correlations in memory consumption and model accuracy.
$endgroup$
– n1k31t4
Feb 8 at 13:55
add a comment |
$begingroup$
The answer will depend on some things such as your hardware and the image you process. Additional, we should distinguish if you are talking about a single run through the network in training mode or in inference mode. In the former, additional parameters are pre-computed and cached as well as several layers, such as dropout, being used, which are simply left out during inference. I will assume you want to simply produce a single prediction for a single image, so we are talking about inference time.
Factors
The basic correlation will be:
- more parameters (i.e. learnable weights, bigger network) - slower than a model with less parameters
- more recurrent units - slower than a convolutional network, which is slower than a full-connected network1
- complicated activation functions - slower than simple ones, such as ReLU
- deeper networks - slower than shallow networks (with same number of parameters) as less run in parallel on a GPU
Having listed a few factors in the final inference time required (time taken to produce one forward run through the network), I would guess that MobileNetV2 is probably among the fastest pre-trained model (available in Keras). We can see from the following table that this network has a small memory footprint of only 14 megabytes with ~3.5 million parameters. Compare that to your VGG test, with its ~138 million... 40 times more! In addition, the main workhorse layer of MobileNetV2 is a conv layer - they are essentially clever and smaller versions of residual networks.
Extra considerations
The reason I included the whole table above was to highlight that with small memory footprints and fast inference times, comes a cost: low accuracies!
If you compute the ratios of top-5 accuracy versus number of parameters (and generally versus memory), you might find a nice balance between inference time and performance.
1 Have a look at this comparison of CNNs with Recurrent modules
answered Oct 4 '18 at 22:31
n1k31t4n1k31t4
6,5512421
$endgroup$
$begingroup$
It is not as simple as looking at the number of parameters and depth. For instance, ResNet50 is significantly faster than Xception on my hardware, despite having more parameters and a higher depth. Similarly, MobileNet is faster than MovileNetV2 for me. That being said, the mobile nets are effectively built for embedded hardware, and thus less demanding.
$endgroup$
– Wok
Feb 8 at 13:02
$begingroup$
@Wok - You're right, which is why I didn't say that. There are many factors, I gave examples. You would need to do some benchmarking of models on target hardware, given certain data. In a very simplistic approach, the number of parameters is a proxy for number of operations, which is why I chose to include that table and also highlight correlations in memory consumption and model accuracy.
$endgroup$
– n1k31t4
Feb 8 at 13:55
add a comment |
$begingroup$
The answer will depend on some things such as your hardware and the image you process. Additional, we should distinguish if you are talking about a single run through the network in training mode or in inference mode. In the former, additional parameters are pre-computed and cached as well as several layers, such as dropout, being used, which are simply left out during inference. I will assume you want to simply produce a single prediction for a single image, so we are talking about inference time.
Factors
The basic correlation will be:
- more parameters (i.e. learnable weights, bigger network) - slower than a model with less parameters
- more recurrent units - slower than a convolutional network, which is slower than a full-connected network1
- complicated activation functions - slower than simple ones, such as ReLU
- deeper networks - slower than shallow networks (with same number of parameters) as less run in parallel on a GPU
Having listed a few factors in the final inference time required (time taken to produce one forward run through the network), I would guess that MobileNetV2 is probably among the fastest pre-trained model (available in Keras). We can see from the following table that this network has a small memory footprint of only 14 megabytes with ~3.5 million parameters. Compare that to your VGG test, with its ~138 million... 40 times more! In addition, the main workhorse layer of MobileNetV2 is a conv layer - they are essentially clever and smaller versions of residual networks.
Extra considerations
The reason I included the whole table above was to highlight that with small memory footprints and fast inference times, comes a cost: low accuracies!
If you compute the ratios of top-5 accuracy versus number of parameters (and generally versus memory), you might find a nice balance between inference time and performance.
1 Have a look at this comparison of CNNs with Recurrent modules
answered Oct 4 '18 at 22:31
n1k31t4n1k31t4
6,5512421
$endgroup$
The answer will depend on some things such as your hardware and the image you process. Additional, we should distinguish if you are talking about a single run through the network in training mode or in inference mode. In the former, additional parameters are pre-computed and cached as well as several layers, such as dropout, being used, which are simply left out during inference. I will assume you want to simply produce a single prediction for a single image, so we are talking about inference time.
Factors
The basic correlation will be:
- more parameters (i.e. learnable weights, bigger network) - slower than a model with less parameters
- more recurrent units - slower than a convolutional network, which is slower than a full-connected network1
- complicated activation functions - slower than simple ones, such as ReLU
- deeper networks - slower than shallow networks (with same number of parameters) as less run in parallel on a GPU
Having listed a few factors in the final inference time required (time taken to produce one forward run through the network), I would guess that MobileNetV2 is probably among the fastest pre-trained model (available in Keras). We can see from the following table that this network has a small memory footprint of only 14 megabytes with ~3.5 million parameters. Compare that to your VGG test, with its ~138 million... 40 times more! In addition, the main workhorse layer of MobileNetV2 is a conv layer - they are essentially clever and smaller versions of residual networks.
Extra considerations
The reason I included the whole table above was to highlight that with small memory footprints and fast inference times, comes a cost: low accuracies!
If you compute the ratios of top-5 accuracy versus number of parameters (and generally versus memory), you might find a nice balance between inference time and performance.
1 Have a look at this comparison of CNNs with Recurrent modules
answered Oct 4 '18 at 22:31
n1k31t4n1k31t4
6,5512421
answered Oct 4 '18 at 22:31
n1k31t4n1k31t4
6,5512421
answered Oct 4 '18 at 22:31
n1k31t4n1k31t4
6,5512421
answered Oct 4 '18 at 22:31
n1k31t4n1k31t4
6,5512421
6,5512421
$begingroup$
It is not as simple as looking at the number of parameters and depth. For instance, ResNet50 is significantly faster than Xception on my hardware, despite having more parameters and a higher depth. Similarly, MobileNet is faster than MovileNetV2 for me. That being said, the mobile nets are effectively built for embedded hardware, and thus less demanding.
$endgroup$
– Wok
Feb 8 at 13:02
$begingroup$
@Wok - You're right, which is why I didn't say that. There are many factors, I gave examples. You would need to do some benchmarking of models on target hardware, given certain data. In a very simplistic approach, the number of parameters is a proxy for number of operations, which is why I chose to include that table and also highlight correlations in memory consumption and model accuracy.
$endgroup$
– n1k31t4
Feb 8 at 13:55
add a comment |
$begingroup$
It is not as simple as looking at the number of parameters and depth. For instance, ResNet50 is significantly faster than Xception on my hardware, despite having more parameters and a higher depth. Similarly, MobileNet is faster than MovileNetV2 for me. That being said, the mobile nets are effectively built for embedded hardware, and thus less demanding.
$endgroup$
– Wok
Feb 8 at 13:02
$begingroup$
@Wok - You're right, which is why I didn't say that. There are many factors, I gave examples. You would need to do some benchmarking of models on target hardware, given certain data. In a very simplistic approach, the number of parameters is a proxy for number of operations, which is why I chose to include that table and also highlight correlations in memory consumption and model accuracy.
$endgroup$
– n1k31t4
Feb 8 at 13:55
$begingroup$
It is not as simple as looking at the number of parameters and depth. For instance, ResNet50 is significantly faster than Xception on my hardware, despite having more parameters and a higher depth. Similarly, MobileNet is faster than MovileNetV2 for me. That being said, the mobile nets are effectively built for embedded hardware, and thus less demanding.
$endgroup$
– Wok
Feb 8 at 13:02
$begingroup$
It is not as simple as looking at the number of parameters and depth. For instance, ResNet50 is significantly faster than Xception on my hardware, despite having more parameters and a higher depth. Similarly, MobileNet is faster than MovileNetV2 for me. That being said, the mobile nets are effectively built for embedded hardware, and thus less demanding.
$endgroup$
– Wok
Feb 8 at 13:02
$begingroup$
@Wok - You're right, which is why I didn't say that. There are many factors, I gave examples. You would need to do some benchmarking of models on target hardware, given certain data. In a very simplistic approach, the number of parameters is a proxy for number of operations, which is why I chose to include that table and also highlight correlations in memory consumption and model accuracy.
$endgroup$
– n1k31t4
Feb 8 at 13:55
$begingroup$
@Wok - You're right, which is why I didn't say that. There are many factors, I gave examples. You would need to do some benchmarking of models on target hardware, given certain data. In a very simplistic approach, the number of parameters is a proxy for number of operations, which is why I chose to include that table and also highlight correlations in memory consumption and model accuracy.
$endgroup$
– n1k31t4
Feb 8 at 13:55
add a comment |
Thanks for contributing an answer to Data Science Stack Exchange!
- 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.
Use MathJax to format equations. MathJax reference.
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%2fdatascience.stackexchange.com%2fquestions%2f39177%2fwhich-is-the-fastest-image-pretrained-model%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
