search

pranoyr / cnn-lstm

CNN LSTM architecture implemented in Pytorch for Video Classification
MIT License
260 stars 46 forks source link

Accuracy drop #7

Open 87nohigher opened 3 years ago

87nohigher commented 3 years ago

Thanks for your great work! I followed the step and running the code successfully. Unfortunately, the learning curve image shown below show that the accuracy drop to 60% validation accuracy, where there is a 30% gap with your learning curve. I don't understand why there are only four label in your tensorboard visualization. All in all, I'm wondering what's the performance you get while training for 101 labels of UCF101, and make sure I got anything wrong. Thanks
cnn_lstm_epoch100

Doge2408 commented 2 years ago

Hello, what is the shape of the data input into the model?Thanks

282517bjiMNqwewed commented 1 year ago

感谢您的出色工作！我按照步骤操作并成功运行了代码。不幸的是，下面显示的学习曲线图像显示准确性下降到 60% 验证准确率，而与您的学习曲线有 30% 的差距。我不明白为什么你的张量板可视化中只有四个标签。总而言之，我想知道您在训练 UCF101 的 101 个标签时获得的性能如何，并确保我做错了什么。谢谢 cnn_lstm_epoch100

hello, may I ask your acc was finally raised?