Update README.md
Browse files
README.md
CHANGED
|
@@ -26,9 +26,9 @@ Please refer to the publication for technical details.
|
|
| 26 |
|
| 27 |
The published model was instantiated with a high-res net (HRnet) backbone and consists of multiple imaging attention modules.
|
| 28 |
Two models were published:
|
| 29 |
-
|
| 30 |
-
|
| 31 |
-
|
| 32 |
|
| 33 |
Input to model is 5D tensor [B, C, T/F, H, W] for batch, channel, time/frame, height and width. Output tensor is in the shape of
|
| 34 |
[B, C-1, T/F, H, W]. The last channel in input is the g-factor map.
|
|
|
|
| 26 |
|
| 27 |
The published model was instantiated with a high-res net (HRnet) backbone and consists of multiple imaging attention modules.
|
| 28 |
Two models were published:
|
| 29 |
+
- SNRAware-small: a 27.7 million parameter model
|
| 30 |
+
- SNRAware-medium: a 55.1 million parameter model
|
| 31 |
+
- SNRAware-large: a 109 million parameter model
|
| 32 |
|
| 33 |
Input to model is 5D tensor [B, C, T/F, H, W] for batch, channel, time/frame, height and width. Output tensor is in the shape of
|
| 34 |
[B, C-1, T/F, H, W]. The last channel in input is the g-factor map.
|