How to rebuild the result of CARS196

[ParsonsZeng]

  Thanks for releasing the code of your work. I have tested on CARS196, but I cannot achieve the performance of your public paper. The highest Recall@1 is 82.4%. I think my setting is wrong so that I cannot achieve the similar performance of your paper. Could you share the setting on CARS196?

The setting is: python train.py --dataset CARS --feature BNInception --embedding 512 512 512 512 512 --ho-dim 8192 8192 8192 8192 --use_horde --trainable --cascaded config.json: { "n_classes_per_batch": 5, "images_per_class": 8, "steps_per_epoch": 200,

"test_batch_size": 100,

"train_lr": 1e-5, "train_epoch": 80,

"workers": 8, "max_queue_size" : 32,

"train_im_size": [256, 256], "test_im_size": [256, 256],

"multi_res_min_ratio": 0.8, "multi_res_max_ratio": 1.8,

"prob_keep_ratio": 1.0, "proba_multi_res": 1.0, "proba_random_crop": 1.0, "proba_horizontal_flip": 0.5,

"resume_training" : null, "compute_scores_freq" : 1 }

And the setting of my PC is Ubuntu18.04, CUDA10.0 with GTX1080ti, Tensorflow 1.14.

[pierre-jacob]

Hi,

Sorry for the delay! After our discussion by e-mail, I retrained the network on the Cars dataset and get the reported results. I used the following parameters that differ from yours:

• loss binomial (add --loss binomial)
• images_per_class = 10
• n_classes_per_batch = 8
• steps_per_epoch = 1000

Training on Cars is slower than Cub, thus the number of steps has to be increased. I suspect that your network was not trained enough. Let me know if this works for you!

[pierre-jacob]

Since this issue has been opened few months ago, and is not active anymore, I hope the given answer has solved this reproducibility issue.

Fell free to re-open an issue otherwise.