question about training the linear classification model about moco HOT 3 CLOSED

The code release in this repo is meant for reproducing the results of research papers.

We help users who have trouble using the code to reproduce results in the paper, but in general we do not provide suggestions on other issues such as how to apply the method to a new task or dataset.

from moco.

Hi，i did unsupervised pre-training of a ResNet-50 model on a dataset which contains 122,208 unlabeled bird images and the last epoch log is below:

the loss stucks at ~6.90 which is similar to another closed issue #12. In that issue it seems not tha bad. Is this normal?

Then i use this pretrained model to train and eval on a dataset which contains 3,959 train images and 2000 val images. These images are in 200 categories of birds. I follow the
'''
python main_lincls.py
-a resnet50
--lr 30.0
--batch-size 256
--pretrained [your checkpoint path]/checkpoint_0199.pth.tar
--dist-url 'tcp://localhost:10001' --multiprocessing-distributed --world-size 1 --rank 0
[your imagenet-folder with train and val folders]
'''
however the validate accuracy is quite low (~12%), which is much lower than supervised training method(~60%). I tried serval learning rate (0.1, 5，10， 100.0) but the results seems still bad.
So can i ask how do you set these hyperparameters？Or, the pretrained model is bad? how can i check this probelm?
Thanks!

Hi, how many GPU did you use for training? I have 8 Tesla v100 (32G) GPU, but it still can not afford batch_size 256.

from moco.

嗨，我在包含 122,208 个未标记鸟类图像的数据集上对 ResNet-50 模型进行了无监督预训练，最后一个纪元日志如下： 损失停留在 ~6.90，这类似于另一个已关闭的问题#12。在那个问题上似乎还不错。这是正常的吗？

然后我使用这个预训练模型对包含 3,959 个训练图像和 2000 个 val 图像的数据集进行训练和评估。这些图像属于 200 种鸟类。我按照 ''' python main_lincls.py -a resnet50 --lr 30.0 --batch-size 256 --pretrained [你的检查点路径]/checkpoint_0199.pth.tar --dist-url 'tcp://localhost:10001 ' --multiprocessing-distributed --world-size 1 --rank 0 [带有 train 和 val 文件夹的 imagenet 文件夹] ''' 但是验证准确度非常低（~12%），远低于监督训练方法（~60%）。我尝试了 serval learning rate (0.1, 5，10, 100.0) 但结果似乎仍然很糟糕。 那请问这些超参数是怎么设置的？ 或者，预训练的模型不好？我如何检查这个问题？ 谢谢！

I also encountered this problem, have you solved it

from moco.