-
Support the following Coordinate Reference Systems and projections when displaying data from external sources, such as WMS:
Coordinate Reference Systems
CRS:84 WGS84 geographic longitude, then latitu…
-
What's the pytorch version for your pre-trained model? My torch version is 1.7.1 but something abour pytorch goes wrong when I ran the script hand_detector_V2.py. Could you please add some information…
-
Hi, I'd like to fine tune my model weights using my own dataset based on your pretrained weights, like dmn_referit_weights.pth, I don't know how to do that because I have no optimizer weights to resum…
-
Pi Node is only supported on Windows on Mac.
It would be nice to be able to run it on a Linux OS
ghost updated
2 weeks ago
-
` File "D:\Cancer\neural-dream\neural_dream\models\googlenet\bvlc_googlenet.py", line 352, in forward
pool5_7x7_s1 = F.avg_pool2d(inception_5b_output, kernel_size=(7, 7), stride=(1, 1), paddi…
-
Hi Ultralytics,
First of all, thank you so much for the interesting work and sharing.
## ❔Question
I mainly have three questions to ask:
1. Size of anchors
![image](https://user-images.githubus…
-
Forward and Backward are done in sequence by layer ID at the moment. In principle, all Forward / Backward steps at the same depth in the DAG can be executed in parallel.
In DAG models where single la…
-
In the pre-trained classifier, why the output layer is not the softmax classifier for classifying 365 labels? Also, are the classifier layers also pre-trained in VGG classifier?
-
**Ryan Franz**
There are always tradeoffs in creating data geared toward visualization alone. Creating a single batched 3D model is likely better performance, but at a loss of flexibility.
So I …
-
Why are you using
```
[yolo]
mask = 3,4,5
...
[yolo]
mask = 1,2,3
```
instead of
```
[yolo]
mask = 3,4,5
...
[yolo]
mask = 0,1,2
```
Besides, is there any plan of releasing Pelee-PR…