Skip to content

simple fix for grid_size in yolov4_head when using custom img_size #7

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

simple fix for grid_size in yolov4_head when using custom img_size #7

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 5 additions & 3 deletions custom_layers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
import tensorflow as tf
from tensorflow.keras import layers, initializers, models
from config import yolo_config


def conv(x, filters, kernel_size, downsampling=False, activation='leaky', batch_norm=True):
Expand Down Expand Up @@ -199,17 +200,18 @@ def yolov4_neck(x, num_classes):


def yolov4_head(yolo_neck_outputs, classes, anchors, xyscale):
size = yolo_config['img_size'][0]
bbox0, object_probability0, class_probabilities0, pred_box0 = get_boxes(yolo_neck_outputs[0],
anchors=anchors[0, :, :], classes=classes,
grid_size=52, strides=8,
grid_size=int(52*(size/416)), strides=8,
xyscale=xyscale[0])
bbox1, object_probability1, class_probabilities1, pred_box1 = get_boxes(yolo_neck_outputs[1],
anchors=anchors[1, :, :], classes=classes,
grid_size=26, strides=16,
grid_size=int(26*(size/416)), strides=16,
xyscale=xyscale[1])
bbox2, object_probability2, class_probabilities2, pred_box2 = get_boxes(yolo_neck_outputs[2],
anchors=anchors[2, :, :], classes=classes,
grid_size=13, strides=32,
grid_size=int(13*(size/416)), strides=32,
xyscale=xyscale[2])
x = [bbox0, object_probability0, class_probabilities0, pred_box0,
bbox1, object_probability1, class_probabilities1, pred_box1,
Expand Down