-
Here is the code:
```class ResNet32(MetaModule):
def __init__(self, num_classes, block=BasicBlock, num_blocks=[5, 5, 5]):
super(ResNet32, self).__init__()
self.in_planes = 16…
-
### 🚀 The feature
Each model implements a function which returns the names of it's features.
### Motivation, pitch
Currently, there is no nice way to extract features of multiple model…
-
I tried to train for 10000 iterations but results are -1
2021-07-02 11:05:55,223 fcos_core INFO: Using 2 GPUs
2021-07-02 11:05:55,223 fcos_core INFO: Namespace(config_file='configs/fcos/fcos_R_50_…
-
Hi,
I'm trying to modify the autoencoder model_layer1.pbtxt file to tie the weights from the hidden layer to the output layer to be the transpose of those from the input layer to the hidden layer. Wh…
-
At the moment there is no such option, as they are always saved (and loaded) from the layer_styles table in "public".
This would make this functionality coherent with the one that allows to save an…
-
**Describe the bug**
Following the [linux quickstart guide](https://www.opencue.io/docs/quick-starts/quick-start-linux/) for spinning up a deployment with docker-compose fails
**To Reproduce**
…
-
Hi I found it confusing when handling multiple inputs of a layer in pipeline parallelism. The lack of flexbility make it difficult to use tuple input. Is there any plans to use dict input?
e.g.
``…
-
Traceback (most recent call last):
File "main/timit_train.py", line 255, in
runner.run()
File "main/timit_train.py", line 144, in run
model = model_fn(args, maxTimeSteps)
File "/mn…
-
In line #L517, nodes of the lowest layer are treated as input nodes for GCN. This suggests the lowest layer contains all the nodes in the sampled sub-graph. However, it is not always true.
For examp…
-
### Is your feature request related to a problem?
Currently, a sprite frames will be called by some seemingly random GUID identifiers, with those identifiers changing when the sprite is re-imported. …