youjiangxu/FaMUS

The result you provided cannot be achieve based on this code.

PoonKinWang opened this issue · 2 comments

PoonKinWang commented

We trained the model with your code and default settings (NL=0.8) but we didn’t achieve the result you provided. The validation log is shown below.

Instructions for updating:
To construct input pipelines, use the `tf.data` module.
INFO:tensorflow:Starting evaluation at 2021-09-02-13:40:44
I0902 21:40:44.409504 139727230316736 evaluation.py:450] Starting evaluation at 2021-09-02-13:40:44
2021-09-02 21:40:44.808432: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10.0
2021-09-02 21:40:45.073419: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7
INFO:tensorflow:Evaluation [20/200]
I0902 21:40:47.569142 139727230316736 evaluation.py:167] Evaluation [20/200]
INFO:tensorflow:Evaluation [40/200]
I0902 21:40:48.506234 139727230316736 evaluation.py:167] Evaluation [40/200]
INFO:tensorflow:Evaluation [60/200]
I0902 21:40:49.461488 139727230316736 evaluation.py:167] Evaluation [60/200]
INFO:tensorflow:Evaluation [80/200]
I0902 21:40:50.409007 139727230316736 evaluation.py:167] Evaluation [80/200]
INFO:tensorflow:Evaluation [100/200]
I0902 21:40:51.340363 139727230316736 evaluation.py:167] Evaluation [100/200]
INFO:tensorflow:Evaluation [120/200]
I0902 21:40:52.284018 139727230316736 evaluation.py:167] Evaluation [120/200]
INFO:tensorflow:Evaluation [140/200]
I0902 21:40:53.217222 139727230316736 evaluation.py:167] Evaluation [140/200]
INFO:tensorflow:Evaluation [160/200]
I0902 21:40:54.177478 139727230316736 evaluation.py:167] Evaluation [160/200]
INFO:tensorflow:Evaluation [180/200]
I0902 21:40:55.141287 139727230316736 evaluation.py:167] Evaluation [180/200]
INFO:tensorflow:Evaluation [200/200]
I0902 21:40:56.100607 139727230316736 evaluation.py:167] Evaluation [200/200]
INFO:tensorflow:Finished evaluation at 2021-09-02-13:40:56
I0902 21:40:56.101341 139727230316736 evaluation.py:456] Finished evaluation at 2021-09-02-13:40:56
test/accuracy[0.284]
total_loss[3.83895969]
INFO:tensorflow:Waiting for new checkpoint at ./output/mini_imagenet_models/resnet32/red_noise_nl_0.8/mentormix//train
I0902 21:44:35.734614 139937759006912 evaluation.py:189] Waiting for new checkpoint at ./output/mini_imagenet_models/resnet32/red_noise_nl_0.8/mentormix//train

We also trained again but got the similar result. Could you give me some advices about that?
Thank you.

vicii0215 commented

I can't gain the Red-miniImageNet dataset and the data files as shown in the author's codes. Could you give me some advices about that?
Thank you.

youjiangxu commented

I can't gain the Red-miniImageNet dataset and the data files as shown in the author's codes. Could you give me some advices about that? Thank you.

hi,
I guess you want to download the red-miniImagenet dataset, and you can refer to the following links:

  1. For getting the dataset to reproduce our results in the paper, please take a look:
    https://storage.googleapis.com/cnlw/README.txt

Or you can look at this link in another project on Mini-ImageNet
https://github.com/youjiangxu/FaMUS/tree/main/baselines/code_mentormix_r32

Best regards,

  • 👍1