Mixing
How fast is TensorFlow compared to self written neural nets?
Clash Royale CLAN TAG#URR8PPP
up vote
1
down vote
favorite
I made my first neural net in C++ without any libraries. It was a net to recognize numbers from the MNIST dataset. In a 784 - 784 - 10 net with sigmoid function and 5 epochs with each 60000 samples, it took about 2 hours to train. It was probably slow anyways, because I trained it on a laptop and I used classes for Neurons and Layers.
To be honest, I've never used Tensor Flow, so I wanted to know how the performance of my net would be compared to the same in Tensor Flow. Not to specific but just a rough aproximation.
neural-networks tensorflow
asked 1 hour ago
Evator
283
add a comment |Â
up vote
1
down vote
favorite
I made my first neural net in C++ without any libraries. It was a net to recognize numbers from the MNIST dataset. In a 784 - 784 - 10 net with sigmoid function and 5 epochs with each 60000 samples, it took about 2 hours to train. It was probably slow anyways, because I trained it on a laptop and I used classes for Neurons and Layers.
To be honest, I've never used Tensor Flow, so I wanted to know how the performance of my net would be compared to the same in Tensor Flow. Not to specific but just a rough aproximation.
neural-networks tensorflow
asked 1 hour ago
Evator
283
add a comment |Â
up vote
1
down vote
favorite
up vote
1
down vote
favorite
I made my first neural net in C++ without any libraries. It was a net to recognize numbers from the MNIST dataset. In a 784 - 784 - 10 net with sigmoid function and 5 epochs with each 60000 samples, it took about 2 hours to train. It was probably slow anyways, because I trained it on a laptop and I used classes for Neurons and Layers.
To be honest, I've never used Tensor Flow, so I wanted to know how the performance of my net would be compared to the same in Tensor Flow. Not to specific but just a rough aproximation.
neural-networks tensorflow
asked 1 hour ago
Evator
283
I made my first neural net in C++ without any libraries. It was a net to recognize numbers from the MNIST dataset. In a 784 - 784 - 10 net with sigmoid function and 5 epochs with each 60000 samples, it took about 2 hours to train. It was probably slow anyways, because I trained it on a laptop and I used classes for Neurons and Layers.
To be honest, I've never used Tensor Flow, so I wanted to know how the performance of my net would be compared to the same in Tensor Flow. Not to specific but just a rough aproximation.
neural-networks tensorflow
neural-networks tensorflow
asked 1 hour ago
Evator
283
asked 1 hour ago
Evator
283
asked 1 hour ago
Evator
283
asked 1 hour ago
Evator
283
asked 1 hour ago
Evator
283
283
add a comment |Â
add a comment |Â
1 Answer
1
active
oldest
votes
up vote
2
down vote
A lot. There are all these optimizations that we might not have thought of like combining layers, functions, etc. I am a pytorch guy though, its clean and doesn't get in your way like tensorflow does.
answered 1 hour ago
user18646
211
New contributor
user18646 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
Alright because that was the main reason i code them myself.I thought tensorflow took too much of my freedom. Is pytorch better in that perspective?
– Evator
43 mins ago
Yes, you will love python way of doing things with PyTorch. Just take the example of guys at Fast.Ai, they started using pytorch when they realised tenaorflow was limiting their creativity for doing things in Deep Learning.
– user18646
35 mins ago
add a comment |Â
1 Answer
1
active
oldest
votes
1 Answer
1
active
oldest
votes
active
oldest
votes
active
oldest
votes
up vote
2
down vote
A lot. There are all these optimizations that we might not have thought of like combining layers, functions, etc. I am a pytorch guy though, its clean and doesn't get in your way like tensorflow does.
answered 1 hour ago
user18646
211
New contributor
user18646 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
Alright because that was the main reason i code them myself.I thought tensorflow took too much of my freedom. Is pytorch better in that perspective?
– Evator
43 mins ago
Yes, you will love python way of doing things with PyTorch. Just take the example of guys at Fast.Ai, they started using pytorch when they realised tenaorflow was limiting their creativity for doing things in Deep Learning.
– user18646
35 mins ago
add a comment |Â
up vote
2
down vote
A lot. There are all these optimizations that we might not have thought of like combining layers, functions, etc. I am a pytorch guy though, its clean and doesn't get in your way like tensorflow does.
answered 1 hour ago
user18646
211
New contributor
user18646 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
Alright because that was the main reason i code them myself.I thought tensorflow took too much of my freedom. Is pytorch better in that perspective?
– Evator
43 mins ago
Yes, you will love python way of doing things with PyTorch. Just take the example of guys at Fast.Ai, they started using pytorch when they realised tenaorflow was limiting their creativity for doing things in Deep Learning.
– user18646
35 mins ago
add a comment |Â
up vote
2
down vote
up vote
2
down vote
A lot. There are all these optimizations that we might not have thought of like combining layers, functions, etc. I am a pytorch guy though, its clean and doesn't get in your way like tensorflow does.
answered 1 hour ago
user18646
211
New contributor
user18646 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
A lot. There are all these optimizations that we might not have thought of like combining layers, functions, etc. I am a pytorch guy though, its clean and doesn't get in your way like tensorflow does.
answered 1 hour ago
user18646
211
New contributor
user18646 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
answered 1 hour ago
user18646
211
New contributor
user18646 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
answered 1 hour ago
user18646
211
answered 1 hour ago
user18646
211
211
New contributor
user18646 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
New contributor
user18646 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
user18646 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
Alright because that was the main reason i code them myself.I thought tensorflow took too much of my freedom. Is pytorch better in that perspective?
– Evator
43 mins ago
Yes, you will love python way of doing things with PyTorch. Just take the example of guys at Fast.Ai, they started using pytorch when they realised tenaorflow was limiting their creativity for doing things in Deep Learning.
– user18646
35 mins ago
add a comment |Â
Alright because that was the main reason i code them myself.I thought tensorflow took too much of my freedom. Is pytorch better in that perspective?
– Evator
43 mins ago
Yes, you will love python way of doing things with PyTorch. Just take the example of guys at Fast.Ai, they started using pytorch when they realised tenaorflow was limiting their creativity for doing things in Deep Learning.
– user18646
35 mins ago
Alright because that was the main reason i code them myself.I thought tensorflow took too much of my freedom. Is pytorch better in that perspective?
– Evator
43 mins ago
Alright because that was the main reason i code them myself.I thought tensorflow took too much of my freedom. Is pytorch better in that perspective?
– Evator
43 mins ago
Yes, you will love python way of doing things with PyTorch. Just take the example of guys at Fast.Ai, they started using pytorch when they realised tenaorflow was limiting their creativity for doing things in Deep Learning.
– user18646
35 mins ago
Yes, you will love python way of doing things with PyTorch. Just take the example of guys at Fast.Ai, they started using pytorch when they realised tenaorflow was limiting their creativity for doing things in Deep Learning.
– user18646
35 mins ago
add a comment |Â
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
StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fai.stackexchange.com%2fquestions%2f8188%2fhow-fast-is-tensorflow-compared-to-self-written-neural-nets%23new-answer', 'question_page');
);
Post as a guest
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
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
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
