Jian Zhang (James)
Jian Zhang (James)
During recent work, I need to train graph embedding along a sequence of time windows. My graph will have new nodes added in a new time window, but most nodes...
我下载了共享的NIPS2014和CVPRd的数据集，发现NIPS的无法解压，CVPR的可以。多次下载，仍然无法解压。是否能再分享一下。谢谢
你好，我仔细看了，这个Generator是在tool目录里的genrator的Genrator这个类。而在训练时，这个Generator并不是Numpy的array或者TF的tensor，所以在下面的代码里（TensorFlow的源码），“ num_samples = int(nest.flatten(data)[0].shape[0]) ”，被调用，从而产生了上面的报错。 请问，你知道是怎么回事吗？如何修复？ if data_utils.is_generator_or_sequence(data) or isinstance( data, iterator_ops.IteratorV2): if isinstance(data, data_utils.Sequence): if steps_per_epoch is None: steps_per_epoch = len(data) return data, steps_per_epoch if isinstance(data, dataset_ops.DatasetV2): return dataset_ops.make_one_shot_iterator(data),...
*Issue #, if available:* *Description of changes:* This PR add a new Jupyter notebook example for demonstrating link prediction pipeline. For the notebook, this PR also adds a simple RGCN...
*Issue #, if available:* *Description of changes:* This PR create a new Jupyter notebook to demonstrate the general APIs for GraphStorm pipeline in a NC task. It also fixed a...
Current issue: In order to reuse GraphStorm's model components, e.g., `InpuLayer`s and `Encoder`s, users need to create a g(DistGraph) first. This create some barrier for users to build customized models...
Current customized label split only support node tasks. Customers need to split edges too for link prediction tasks.
The current GraphStorm `Evaluator`s have misleading naming convention and lack of default metric. The new `Evaluator`s will be task-specific. Sample code ``` evaluator = gs.eval.GSgnnClassificationEvaluator(eval_frequency=100) ``` **Requested changes** 1. Create...
For a classification task, cannot use all metrics at the same time. Examples: Accuracy and auc_roc requires different prediction return values. Therefore they cannot be used in one training/evaluation epoch....
Tis Demo FR want to illustrate: 1. there is an existing pipeline for sample-independent deep learning task, e.g., image classification with Pytorch. 2. the deep learning task want to include...