jhhuang96 / convlstm-pytorch Goto Github PK

Hello, awesome repo.
I have been playing with various convlstm/gru implementation as we don't have an official one in Pytorch.
I am having trouble getting good images as output. I am unable to get sharp images as the ones you showed.
I modified your model to output 2 classes per image, to produce binary values and train with CrossEntropy (I just put to 1 all pixels greater that 0.5, and zero the others).
I am also currently trying this UpsampleBlock from fastai2 Unet for the decoder with good results:

class UpsampleBlock(Module):
    "A quasi-UNet block, using `PixelShuffle_ICNR upsampling`."
    @delegates(ConvLayer.__init__)
    def __init__(self, in_ch, out_ch, final_div=True, blur=False, act_cls=defaults.activation,
                 self_attention=False, init=nn.init.kaiming_normal_, norm_type=None, **kwargs):
        self.shuf = PixelShuffle_ICNR(in_ch, in_ch//2, blur=blur, act_cls=act_cls, norm_type=norm_type)
        ni = in_ch//2
        nf = out_ch
        self.conv1 = ConvLayer(ni, nf, act_cls=act_cls, norm_type=norm_type, **kwargs)
        self.conv2 = ConvLayer(nf, nf, act_cls=act_cls, norm_type=norm_type,
                               xtra=SelfAttention(nf) if self_attention else None, **kwargs)
        self.relu = act_cls()
        apply_init(nn.Sequential(self.conv1, self.conv2), init)

    def forward(self, up_in):
        up_out = self.shuf(up_in)
        return self.conv2(self.conv1(up_out))

decoder的第一层输入都是初始化的么？

After the program has run the training dataset and validation dataset normally, no corresponding test.py program is found, is there still this part of the program or am I misunderstanding it and can be done in the existing program?

窥视孔连接哪里去了呀？ it、ft应该有Ct-1的信息，ot应该有Ct的信息呀

你好，请问是使用默认的batch_size=4吗，为什么跑了好久他的loss都不收敛，都是在0.010-0.019左右波动，大概需要跑多少个epoch才会收敛呢？

期待回复！！！

Could anyone offer a solution. Many thanks.

convlstm好像没有按照论文那种**，而是直接套用trajgru的encoder-forcaster结构么？我看预测器状态都是从高维传递

大佬，我注意到您在每个cell之间还加了一层卷积和leaky relu这是为什么呢?

how to use this code to do some research on industrial process monitoring

请问大佬您这个模型的数据集可以用ERA5再分析数据集吗？，请问最后预测有可视化结果吗？