Hi, I have 3 questions here Using the code p

Hi, <a class="user-mention notranslate" data-hovercard-type="user" data-hovercard-url=

Hi Zhiyong, Thanks for the prompt reply. <span class="email-hidden

<a class="user-mention notranslate" data-hovercard-type="user" data-hovercard-url="/us

Batch size vs rank 1 about open-reid HOT 5 CLOSED

cysu commented on May 26, 2024

Batch size vs rank 1

from open-reid.

Comments (5)

zydou commented on May 26, 2024

Hi, @cptay

In my experiments, running a batch size of 256 gives me ~67% mAP and ~84% rank 1. Larger batch size will get better results.
I'm not sure about it.
Pytorch is not officially supported on Windows. The code running on Linux works perfectly.

from open-reid.

cptay commented on May 26, 2024

Hi Zhiyong, Thanks for the prompt reply.

…

On Tue, Oct 10, 2017 at 4:33 PM, Zhiyong Dou ***@***.***> wrote: Hi, @cptay <https://github.com/cptay> 1. In my experiments, running a batch size of 256 gives me ~67.9% mAP and ~84% rank 1. Larger batch size will get better results. 2. I'm not sure about it. 3. Pytorch is not officially supported on Windows. The code running on Linux works perfectly. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#28 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AbdWmB72jETPmx92wI9r_DYCbSBRvYrCks5sqyvigaJpZM4PziyT> .

from open-reid.

Cysu commented on May 26, 2024

@zydou Thanks very much for your answer!

@cptay

Larger batch size works better for triplet loss, since you can find harder negative samples.
The effective of using normalization could be very minor.
Sorry but I have no experience with PyTorch on Windows.

from open-reid.

cptay commented on May 26, 2024

Hi, May I know if you used test-time augmentation during evaluation? Thanks

…

On Wed, Oct 11, 2017 at 4:11 AM, Tong Xiao ***@***.***> wrote: @zydou <https://github.com/zydou> Thanks very much for your answer! @cptay <https://github.com/cptay> 1. Larger batch size works better for triplet loss, since you can find harder negative samples. 2. The effective of using normalization could be very minor. 3. Sorry but I have no experience with PyTorch on Windows. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#28 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AbdWmEDTgnP69sLQi1QruwYE7QHgaTKFks5sq89igaJpZM4PziyT> .

from open-reid.

Cysu commented on May 26, 2024

@cptay No we don't have data augmentation for test evaluation. Just resizing and normalizing the whole image at here.

from open-reid.

Recommend Projects