Commit
•
6ea8797
1
Parent(s):
efdbe41
Update README.md
Browse files
README.md
CHANGED
@@ -12,9 +12,13 @@ tags:
|
|
12 |
---
|
13 |
|
14 |
This model is designed for detecting throw capture moments in Tekken 8 gameplay.
|
|
|
15 |
It is based on the VGG16 architecture, modified by removing the top layer to serve as a feature extractor.
|
|
|
16 |
The model was trained using Keras on a dataset comprising video compilations from Tekken 8 fights, resulting in a total of 701,990 images at a resolution of 640x360. Approximately 5,000 of these images feature throw captures. Training involved augmentation techniques such as slight color shifting and the addition of mild color or black-and-white noise to enhance model robustness.
|
17 |
|
18 |
The model underwent 65 training cycles, each consisting of 13 epochs.
|
|
|
19 |
In each cycle, a batch of 250 randomly selected images from the dataset was used, with at least 40 images depicting throw captures. The batch size was set to 20.
|
|
|
20 |
The custom top layer added for this task includes a Flatten layer followed by a Dense layer with 128 units and 'relu' activation, a Dropout layer with a rate of 0.4, and a final Dense layer with 1 unit and 'sigmoid' activation to predict throw captures.
|
|
|
12 |
---
|
13 |
|
14 |
This model is designed for detecting throw capture moments in Tekken 8 gameplay.
|
15 |
+
|
16 |
It is based on the VGG16 architecture, modified by removing the top layer to serve as a feature extractor.
|
17 |
+
|
18 |
The model was trained using Keras on a dataset comprising video compilations from Tekken 8 fights, resulting in a total of 701,990 images at a resolution of 640x360. Approximately 5,000 of these images feature throw captures. Training involved augmentation techniques such as slight color shifting and the addition of mild color or black-and-white noise to enhance model robustness.
|
19 |
|
20 |
The model underwent 65 training cycles, each consisting of 13 epochs.
|
21 |
+
|
22 |
In each cycle, a batch of 250 randomly selected images from the dataset was used, with at least 40 images depicting throw captures. The batch size was set to 20.
|
23 |
+
|
24 |
The custom top layer added for this task includes a Flatten layer followed by a Dense layer with 128 units and 'relu' activation, a Dropout layer with a rate of 0.4, and a final Dense layer with 1 unit and 'sigmoid' activation to predict throw captures.
|