-
Notifications
You must be signed in to change notification settings - Fork 4
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Detailed preprocess dataset and format about AVE-Dataset #7
Comments
I have processed the AVE-Dataset using the preprocess.py, and generate trainset. But the loss did not decrease during the training phase. |
Hi, Thank you for your interest in my code and project. Data preprocessingIn my case, I first directly downloaded videos from YouTube using With the above naming convention, when you configure some path settings into config.ini file and then run
For more details, you can refer to Loss not decreasingI also faced this issue. This issue seems to occur because the last fully connected layer is so tiny and so vulnerable to noisy data, compared to other layers. Once the last fully connected layer is misguided, it may never be recovered to the expected state. Here are some several tips that might help you. However, please remind that the network is not always successfully trained even though you apply all the solutions below. 1. Learning Rate 2. Use Larger Batch 3. In case of training AVE-Net: Tweak the parameter of the last fully connected layer Please change this part like given below. objects-that-sound/model/avenet.py Lines 24 to 25 in d19f971
self.fc3 = nn.Linear(1, 2)
self.fc3.weight.data[0] = -0.7
self.fc3.weight.data[1] = 0.7
self.fc3.bias.data[0] = 1.2
self.fc3.bias.data[1] = -1.2 4. One more tip Comment: Pretrained model is available! Please use them if you need. If you have any questions or have any more issues, feel free to contact me. Sincerely, Kyuyeon. |
Thanks for sharing your great job.
Can you provide the detailed process of preprocessing AVE-dataset?
The text was updated successfully, but these errors were encountered: