wentao

Can a dynamic input dimension be supported ？

2

Can a dynamic input dimension be supported ？ For example： input size 1 ：1x608x608x3 input size 2 ：1x352x352x3 input size 3 ：1x320x320x3

Pre-trained models (20170512-110547) VS Pre-trained models (20180402-114759)

8

Hello, David! First of all, thank you very much for sharing the pre-training model, which is very helpful to my learning.I just tested your new version of pre-training model (20180402-114759),...

How to test my pictures with the model you trained?

1

Hello, author! At present, I want to test my own pictures through the model you trained. There is no label for my pictures. Can I test this? If so, how...

Does it support python api? In a similar way to trtexec, transfer the engine model and do inference？

1

### Description ```shell Does it support python api? In a similar way to trtexec, transfer the engine model and do inference？ ``` ### Reproduced Steps ```shell Does it support python...

training

7

Hello! I would like to ask if your training code can be used to train ILSVRC-2012 dataset？ Thank you！

why need add this layer？

1

hi！ First of all, thank you very much for your open source code. Then, when I was looking at the code, I found that I didn't understand one sentence. Could...

Have you compared the effects of topformer and swin transformer ?

2

Hi! Excuse me, have you compared the speed and accuracy of topformer and swin transformer under the same computing power? Looking forward to your reply. good luck!

Is batchsize>1 supported in convert2onnx.py file?

1

Hi! Thank you so much for your open source project, it's great！ I encountered a problem when verifying its performance, as follows: When I want to test batchsize=2, convert the...

您好！ 我这边最近尝试复现您开源的基于MQBench下的NNIE量化方式，为了解决在海思芯片上算法量化精度掉点的问题。 然后，我这边复现的时候遇到了如下问题： 1.common.py中C3模块的问题，导致报错，修改为官方v6.0版本的C3模块解决。 2.AttributeError: 'GraphModule' object has no attribute 'module'  暂未解决，我看到其他开发者也遇到了类似问题，如下： https://github.com/Gumpest/YOLOv5-Multibackbone-Compression/issues/83 能帮忙指导一下吗？谢谢~