RT-DETR
RT-DETR copied to clipboard
lyuwenyu
How does the pytorch version test GFLOPs and FPS, author
Star RTDETR 请先在RTDETR主页点击star以支持本项目 Star RTDETR to help more people discover this project.
Describe the bug A clear and concise description of what the bug is. If applicable, add screenshots to help explain your problem.
To Reproduce Steps to reproduce the behavior.
You can use torch.profiler
https://pytorch.org/tutorials/recipes/recipes/profiler_recipe.html
Hello author, I understand what you mean, but I used the model variable in the model to test the model of the model on the 3090 device, the input is (1,13,640,640), and the gflops of the test R18RTDETR is 30, I don't know if this is probably correct or not
I just don't know how long it takes to calculate FPS and GFLIPs in RTDETR plus post-processing process
Dear Author,
I downloaded the rtdetr_r50vd model you provided to calculate the GFLOPs with an input of (1, 3, 640, 640). The result I obtained was only 69 GFLOPs, which is significantly different from the 108 GFLOPs mentioned on your homepage. Why is there such a discrepancy? What was the input data size used in your tests? I look forward to your response.
你好，我之前得到的结果是图片大小为512512的，用640640的和原作者的是一致的
---Original--- From: @.> Date: Wed, Nov 6, 2024 20:31 PM To: @.>; Cc: @.@.>; Subject: Re: [lyuwenyu/RT-DETR] How does the pytorch version test GFLOPs andFPS, author (Issue #401)
Dear Author,
I downloaded the rtdetr_r50vd model you provided to calculate the GFLOPs with an input of (1, 3, 640, 640). The result I obtained was only 69 GFLOPs, which is significantly different from the 108 GFLOPs mentioned on your homepage. Why is there such a discrepancy? What was the input data size used in your tests? I look forward to your response.
Do you have the answer yet, I got almost 68 GFlops as well
— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you were mentioned.Message ID: @.***>
不是不是😂是我搞错了，我记得我当时是用的训练图片大小不一样所以FLOPS才和官方文档里不一样，但是我一开始没发现，之后用和官方一样大小的图就是一致的
---Original--- From: @.> Date: Wed, Nov 6, 2024 20:41 PM To: @.>; Cc: @.@.>; Subject: Re: [lyuwenyu/RT-DETR] How does the pytorch version test GFLOPs andFPS, author (Issue #401)
你好，我之前得到的结果是图片大小为512512的，用640640的和原作者的是一致的 … ---Original--- From: @.> Date: Wed, Nov 6, 2024 20:31 PM To: @.>; Cc: @.@.>; Subject: Re: [lyuwenyu/RT-DETR] How does the pytorch version test GFLOPs andFPS, author (Issue #401) Dear Author, I downloaded the rtdetr_r50vd model you provided to calculate the GFLOPs with an input of (1, 3, 640, 640). The result I obtained was only 69 GFLOPs, which is significantly different from the 108 GFLOPs mentioned on your homepage. Why is there such a discrepancy? What was the input data size used in your tests? I look forward to your response. Do you have the answer yet, I got almost 68 GFlops as well — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you were mentioned.Message ID: @.***>
您好，您的意思是作者原来搞错了吗？68GFLOPs是512*512的？
— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you were mentioned.Message ID: @.***>
不好意思，我不太清楚，我用的是pytorch
---Original--- From: @.> Date: Wed, Nov 6, 2024 20:51 PM To: @.>; Cc: @.@.>; Subject: Re: [lyuwenyu/RT-DETR] How does the pytorch version test GFLOPs andFPS, author (Issue #401)
不是不是😂是我搞错了，我记得我当时是用的训练图片大小不一样所以FLOPS才和官方文档里不一样，但是我一开始没发现，之后用和官方一样大小的图就是一致的 … ---Original--- From: @.> Date: Wed, Nov 6, 2024 20:41 PM To: @.>; Cc: @.@.>; Subject: Re: [lyuwenyu/RT-DETR] How does the pytorch version test GFLOPs andFPS, author (Issue #401) 你好，我之前得到的结果是图片大小为512512的，用640640的和原作者的是一致的 … ---Original--- From: @.> Date: Wed, Nov 6, 2024 20:31 PM To: @.>; Cc: @.@.>; Subject: Re: [lyuwenyu/RT-DETR] How does the pytorch version test GFLOPs andFPS, author (Issue #401) Dear Author, I downloaded the rtdetr_r50vd model you provided to calculate the GFLOPs with an input of (1, 3, 640, 640). The result I obtained was only 69 GFLOPs, which is significantly different from the 108 GFLOPs mentioned on your homepage. Why is there such a discrepancy? What was the input data size used in your tests? I look forward to your response. Do you have the answer yet, I got almost 68 GFlops as well — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you were mentioned.Message ID: @.> 您好，您的意思是作者原来搞错了吗？68GFLOPs是512512的？ — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you were mentioned.Message ID: @.*>
您好，我跑的最初的paddle 代码RTDETR r50，测出68GFLOPS，为啥现在是一百多呀，你知道吗
— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you were mentioned.Message ID: @.***>