bk

There are missing parameters in the given code I suppose, 1- class Encoder() , has missing arguments in __init__() 2- h = o * torch.tanh(F.conv2d(torch.cat((c,M), dim= ),self.weight_1x1)), dim is missing...

Why Wci, Wcf, Wco are Variables rather than nn.Parameters

3

Is there any reason for initializing Wci_o_f in ConvLSTMCell as autograd Variables rather than nn.Parameters

Different gradients for HyperNet training

2

TLDR: Is there a way to optimize model created by combine_state_for_ensemble using torch.backward()? Hi, I am using combine_state_for_ensemble for HyperNet training. ``` fmodel, fparams, fbuffers = combine_state_for_ensemble([HyperMLP() for i in...

Finetuning with different max_seq_len and patch_size

1

### Discussed in https://github.com/SalesforceAIResearch/uni2ts/discussions/181 Originally posted by **bkoyuncu** February 6, 2025 Hi, I want to load a pretrained model however with different max_seq_len and path_sizes to be used. I have...

Problem when Pretrainig the model with past_feat_dynamic_real

2

### Discussed in https://github.com/SalesforceAIResearch/uni2ts/discussions/169 Originally posted by **bkoyuncu** January 8, 2025 Hello, I have created my data with past_feat_dynamic_real, however, I believe the current implementation in pretrain.py does not include...

Hi, Can someone guide me where to get the datasets for 3D experiments for example cars?