I want a parameter configuration that reproduces the results

[yup1212]

Using the operating instructions you provided and the parameter settings in the documentation did not reproduce the results, The parameter settings in the article are even less effective. Can you provide a parameter setting that achieves the effect in the article and put it in the document.

Evaluating market1501 (source)

Extracting features from query set ... Done, obtained 3368-by-512 matrix Extracting features from gallery set ... Done, obtained 15913-by-512 matrix Speed: 0.0299 sec/batch Computing distance matrix with metric=euclidean ... Computing CMC and mAP ... ** Results ** mAP: 78.0% CMC curve Rank-1 : 91.3% Rank-5 : 96.8% Rank-10 : 97.9% Rank-20 : 98.8% Checkpoint saved to "log/osnet_x1_0-softmax-market1501/model/model.pth.tar-64"

has converged

=> Final test

Evaluating market1501 (source)

Extracting features from query set ... Done, obtained 3368-by-512 matrix Extracting features from gallery set ... Done, obtained 15913-by-512 matrix Speed: 0.0299 sec/batch Computing distance matrix with metric=euclidean ... Computing CMC and mAP ... ** Results ** mAP: 78.1% CMC curve Rank-1 : 91.3% Rank-5 : 96.8% Rank-10 : 97.9% Rank-20 : 98.8% Checkpoint saved to "log/osnet_x1_0-softmax-market1501/model/model.pth.tar-100"

Total params: 2,578,879 Trainable params: 2,578,879 Non-trainable params: 0 Input size (MB): 0.38 Forward/backward pass size (MB): 282.45 Params size (MB): 9.84 Estimated Total Size (MB): 292.66 Loading checkpoint from "******************************/model.pth.tar-100" Loaded model weights Loaded optimizer Last epoch = 100 Last rank1 = 91.3% dist_metric='cosine'

Evaluating dukemtmcreid (target)

Extracting features from query set ... Done, obtained 2228-by-512 matrix Extracting features from gallery set ... Done, obtained 17661-by-512 matrix Speed: 0.0303 sec/batch Computing distance matrix with metric=cosine ... Computing CMC and mAP ... ** Results ** mAP: 24.3% CMC curve Rank-1 : 41.7% Rank-5 : 57.7% Rank-10 : 63.3% Rank-20 : 69.0%

[klahaag]

Do you get the same results each training run with the same settings? For us, we do get different results with each training run: https://github.com/KaiyangZhou/deep-person-reid/issues/485

However, we get very close to paper results: Market1501: mAP: 86.6 / Rank1: 95.1 MSMT17: mAP: 52.6 / Rank1: 77.6

Config: Base_config: https://github.com/KaiyangZhou/deep-person-reid/blob/master/configs/im_osnet_x1_0_softmax_256x128_amsgrad_cosine.yaml Train: transforms: [random_flip, random_erase]

Test dist_metric: cosine

[yup1212]

thanks for the reply My training results are the same every time. I use the configuration described on the home page directly from the source code. https://github.com/KaiyangZhou/deep-person-reid

[kwaylee]

hello, I also can't get the paper experience result, do you have to get it? I really want to know the parameter settings that can get the same results, thank you very much.

[shayan-aqabarary]

hello, I also can't get the paper experience result, do you have to get it? I really want to know the parameter settings that can get the same results, thank you very much.

Please send me an email, I am working on this problem and I want to correct this problem and then I try to . my mail address: shayan[dot]aqabarary[at]gmail[dot]com