cannot reproduce comparable results in the paper
felix-yuxiang opened this issue · comments
Hi, I ran the code with a single GPU NVIDIA GeForce RTX 3090 with the given config file listed in the paper. Here is my reproduced result which is significantly different from the results provided in README.md file. Can you guide me through and specify what could be the issue? Can you provide more info on how to train a model with the same performance of your pre-trained model you provided in /checkpoints. Any help will be appreciated.
I also have the similar result while reproducing the training.
I think it's due to the hyperparameters setting. In the paper it's mentioned "With a frozen denoising module, we then train the leapfrog initializer for 200 epochs with an initial learning rate of 10−4, decaying by 0.9 every 32 epochs", but in the default led_augment.yml it is not like this.
Set them based on the paper and I've got
I think it's due to the hyperparameters setting. In the paper it's mentioned "With a frozen denoising module, we then train the leapfrog initializer for 200 epochs with an initial learning rate of 10−4, decaying by 0.9 every 32 epochs", but in the default led_augment.yml it is not like this.
Set them based on the paper and I've got
Hello, did you use the pre trained model provided by him for the diffusion model in the first stage, or did you train yourself for one stage according to the settings in the paper?
I think it's due to the hyperparameters setting. In the paper it's mentioned "With a frozen denoising module, we then train the leapfrog initializer for 200 epochs with an initial learning rate of 10−4, decaying by 0.9 every 32 epochs", but in the default led_augment.yml it is not like this.
Set them based on the paper and I've gotHello, did you use the pre trained model provided by him for the diffusion model in the first stage, or did you train yourself for one stage according to the settings in the paper?
Hi, I use the provided pre-trained model as the first stage.
I think 0.83/1.69 was the only reproduced result
Now, I am able to reproduce their stageone and LED stagetwo results. The answer from @woyoudian2gou helped me a lot. But I would say it requires an non-trivial amount of engineering work to tune this well.
Could you share with us some insight, it would me helpful.
Now, I am able to reproduce their stageone and LED stagetwo results. The answer from @woyoudian2gou helped me a lot. But I would say it requires an non-trivial amount of engineering work to tune this well.
Yes, and the whole implementation is difficult to explain, I think the original
author may have used a different method to get the pre-trained model.
@woyoudian2gou Hi, I have implemented your mentioned hyperparameters setting, but still can't get a reasonable result. So could you share your config.yml with us? Thank you very much.
@woyoudian2gou Hi, I have implemented your mentioned hyperparameters setting, but still can't get a reasonable result. So could you share your config.yml with us? Thank you very much.
@kkk00714 Thank you for your prompt reply, I would also like to know the hyperparameters of Phase 2 training, could you share that? I would appreciate it