shuyansy / Detect-and-read-meters

This is the first released system towards complex meters` detection and recognition, which is implemented by computer vision techniques.
MIT License
110 stars 15 forks source link

Can you share the weight or training code? #3

Open karryor opened 1 year ago

karryor commented 1 year ago

Dear author, in your paper, the prediction effect is the best when the backbone network is resnet network. Could you please share the weight when the backbone network is resnet network, or share the training code? Thank you very much!

karryor commented 1 year ago

When I used the weights you shared to make predictions, the readings of some images were not very accurate, so I would like to try the best method mentioned in your paper

shuyansy commented 1 year ago

ok,i will release the training code as soon as possible

发自我的iPhone

------------------ Original ------------------ From: karryor @.> Date: Thu,May 25,2023 4:53 PM To: shuyansy/A-detection-and-recognition-pipeline-of-complex-meters-in-wild @.> Cc: Subscribed @.***> Subject: Re: Re:[shuyansy/A-detection-and-recognition-pipeline-of-complex-meters-in-wild] Canyou share the weight or training code? (Issue #3)

When I used the weights you shared to make predictions, the readings of some images were not very accurate, so I would like to try the best method mentioned in your paper

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you are subscribed to this thread.Message ID: @.***>

karryor commented 1 year ago

ok,i will release the training code as soon as possible 发自我的iPhone ------------------ Original ------------------ From: karryor @.> Date: Thu,May 25,2023 4:53 PM To: shuyansy/A-detection-and-recognition-pipeline-of-complex-meters-in-wild @.> Cc: Subscribed @.> Subject: Re: Re:[shuyansy/A-detection-and-recognition-pipeline-of-complex-meters-in-wild] Canyou share the weight or training code? (Issue #3) When I used the weights you shared to make predictions, the readings of some images were not very accurate, so I would like to try the best method mentioned in your paper — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you are subscribed to this thread.Message ID: @.>

ok, thank you very much