WENZHE LIU

> @rrryan2016 > In this notebook, I show you how to get 73% with resnet34 only. > > https://colab.research.google.com/drive/1LbDiAs5xOmhwaoKtJepaK_oVU_IkgLM8?usp=sharing Grateful, it is helpful!

Could the author provide the pretrained model on Carvana? :)

Has the author already provided pretrained weights?

I guess the problem may be that my backbone is not well trained, as it could extract detailed features as shown in the illustration pictures. The pretrained on part of...

I well-trained my backbone again, as below: | | Baseline Baseline | My backbone | |-----------------|-------------------|-------------| | Train TOP1 Acc. | 83.792 | 81.660 | | Train TOP5 Acc. |...

After I training on Market1501, the evaluation results turn to be, > =========> Test on dataset: market1501 Extracting feature... > 1000/1000 batches done, +0.58s, total 30.42s > Done, 30.58s >...

If I change the renset50 to Densenet121, and do training, it comes out like, > > Extracting feature... > 1000/1000 batches done, +0.77s, total 39.60s > Done, 39.70s > Computing...

Much better results when using densenet121 instead of resnet50 as above: > ... > Epoch: [300][90/93] Time 0.178 (0.203) Data 0.001 (0.004) Loss 0.0422 (0.0826) CLoss 0.0422 (0.0768) GLoss 0.0000...

> > > 你好，请问你找到问题的原因了吗 not yet

> Hi, @KleinXin , thanks for your interest of our work. As you mentioned that it is a different dataset and task. the hyperparamters need to be consistent with your...