From 0595f761eea77342f604e5633e745ebcdd82f7cb Mon Sep 17 00:00:00 2001
From: Sun Jiao
Date: Wed, 18 Dec 2024 23:04:55 +0800
Subject: [PATCH] Update comments regarding difference among object detection
models
---
docs/source/models.rst | 1 +
1 file changed, 1 insertion(+)
diff --git a/docs/source/models.rst b/docs/source/models.rst
index 53e8d87609e..1e3a27f9f9a 100644
--- a/docs/source/models.rst
+++ b/docs/source/models.rst
@@ -420,6 +420,7 @@ Here is an example of how to use the pre-trained object detection models:
# Step 1: Initialize model with the best available weights
weights = FasterRCNN_ResNet50_FPN_V2_Weights.DEFAULT
+ # for FCOS, RetinaNet, SSD and SSDlite, use `score_thresh=0.9`.
model = fasterrcnn_resnet50_fpn_v2(weights=weights, box_score_thresh=0.9)
model.eval()