-
### 🐛 Describe the bug
i'm building a GNN model using pytorch geometric for multicalssifiction of molécule edges.
this is the code model.
`class GCN(torch.nn.Module):
def __init__(self, f…
-
## ❓ Questions & Help
Hi,
I am using "early stopping" for a GraphConvModel model.
```
import deepchem as dc
tasks, datasets, transformers = dc.molnet.load_delaney(featurizer='GraphConv')
t…
-
尊敬的作者您好，阅读了您的代码和论文感觉非常棒！因为我想把PMP改成PYG实现，但有遇到了一个小问题不是很确定，所以想冒昧请教一下，请问把PMP套在nn.GraphConv外面能实现吗，这样改动就会小一些，还是必须从消息传递处进行修改呀。如果可以这样是可行的，将节省大量的时间。期待您的回复，感谢！
-
Hi, there are some updates to the Spektral's Convolutional layers:
A_in = Input(tensor=sp_matrix_to_sp_tensor(fltr)) will lead to failure
And GraphConv has been removed as well.
I will be r…
-
## 🚀 Feature
We should implement NN modules as functions to allow building models with dynamically generated weights.
## Motivation
As discussed in #3190, EvolveGCN is a typical example where GCN…
-
I have a use case where I would like to plot training loss during training of a model in deepchem. Currently, to access the training loss for every iteration, I should enable logging in the script and…
-
## 🐛 Bug
Dropout layers are not activated when `predict_uncertainty` is called in some models, so the epistemic component of the uncertainty is not calculated. I think the models based on KerasMod…
-
I have encountered such a mistake：
Traceback (most recent call last):
File "main.py", line 6, in
from models.losses import chamfer_distance
File "/home/lab505/gpu_point2mesh/models/loss…
-
## ❓ Questions & Help
Essentially the title. Is it possible to do node-property prediction (i.e. atom-property prediction if the graph is a molecule) in DeepChem?
If not, do you have any suggest…
-
Let me begin with a simple code snippet:
```python
import deepchem as dc
tasks, datasets, transformers = dc.molnet.load_delaney(featurizer='GraphConv')
train_dataset, valid_dataset, test_dataset =…