-
Namespace(dropout=0.2, evaluate_every=500, gpu=-1, grad_norm=1.0, graph_batch_size=30000, graph_split_size=0.5, lr=0.01, n_bases=4, n_epochs=10000, negative_sample=1, regularization=0.01)
load data f…
-
Hello. ThanksHello everyone,
First of all, thank you for sharing such a good implementation. It seems that there is a bug in the utils.py file in the utils directory. The code is as follows:
```py…
-
**Describe the bug**
I am analyzing topological similarity between two nodes and their networks using the FastRP algorithm. My objective is to make controlled changes to the network, rerun FastRP, an…
-
I have a fine-tuned EfficientNet Lite0 model from timm, which I quantized using QAT FX Graph Mode in PyTorch. When I test images containing the same object in both PyTorch and Dart, I get different cl…
-
After TensorFlow graph support is added (i.e. #4), we will need to adapt the existing miniKanren relations to TF[P] objects.
This might require a core set of linear/tensor-algebraic graph normaliza…
-
I'm unable to iterate deterministically. I've looked at [this page](https://www.tensorflow.org/datasets/determinism#get_deterministic_file_shuffling) and I've tried to set up the config so it iterates…
-
## Description
Cosine similarity is one of the more popular space types. faiss does not support it directly. Instead, they prefer to have data be normalized and then use the inner product (which is…
-
In this function, there is an if block as follows:
if config.USE_MINI_MASK:
y1, x1, y2, x2 = tf.split(positive_rois, 4, axis = 1)
gt_y1, gt_x1, gt_y2, gt_x2 = tf.spl…
-
In a previous issue, I discussed one reason why eigenvector centralization is problematic: #2673 (it depends on the normalization of the vertex-level centralities).
There are other conceptual probl…
-
### What happens, and what did you expect instead?
The `betweenness` documentation states under the `normalized` argument that
> If `TRUE`, then the results are normalized by the number of ordere…