Xuesong Wang

You don't have to use the data pipeline to process the data, you can use tensorflow_datasets or keras.datasets to load the input data, unless the data you are training on...

I am having the same issue here. I guess it's because when we build densenet model, in the DenseBlock __init__ method, we use a list to store the layers, but...

> > 我在这里也有同样的问题。我想是因为当我们建立密度模型时，在DenseBlock中**依尼特**方法时，我们使用一个列表来存储层，但如果要使用检查点保存模型，则不允许这样做。如果我们以.h5格式保存检查点，这是可以的，但是如果我们使用默认格式保存，这是不行的。 > > 我试图用函数而不是子类来编写DenseBlock，这个问题仍然存在。我还在想怎么走来走去。 > > 在TensorFlow问题中也提到了这个问题，[TensorFlow/TensorFlow#36916](https://github.com/tensorflow/tensorflow/issues/36916) > > ``` > > class DenseBlock(tf.keras.layers.Layer): > > def __init__(self, num_layers, growth_rate, drop_rate): > > super(DenseBlock, self).__init__() > > self.num_layers...

选用的learning rate合适吗？改变learning rate效果有改变吗？ @Jaren1907 @MingKeYue

> > 选用的learning rate合适吗？改变learning rate效果有改变吗？ @Jaren1907 @MingKeYue > > 没见哪里可以设置learning rate的额 在train.py里有optimizer，它是有默认参数的，只不过没有写。 ``` optimizer = tf.keras.optimizers.RMSprop() ``` 参见这里： [RMSProp](https://www.tensorflow.org/versions/r2.3/api_docs/python/tf/keras/optimizers/RMSprop)

> > > > 选用的learning rate合适吗？改变learning rate效果有改变吗？ @Jaren1907 @MingKeYue > > > > > > > > > 没见哪里可以设置learning rate的额 > > > > > > 在train.py里有optimizer，它是有默认参数的，只不过没有写。 > > ```...

I am also see this bug, installed dlg from pip, 2.2.1+cu121, for torch 2.2.2+cu121. Also tried for torch 2.3.x, not working.

> > I am also see this bug, installed dlg from pip, 2.2.1+cu121, for torch 2.2.2+cu121. Also tried for torch 2.3.x, not working. > > Did you install torch with...

> @Davidxswang could you share your pip install command? and what is the version if check with `pip list|grep torch` and `torch.__version__` in your case? `pip install torch==2.2.2 torchvision==0.17.2 torchaudio==2.2.2...