Use resnet18 due to RAM limitation

QasimKhan5x · web-flow · commit 110f0a9c729c · 2023-06-02T15:59:14.000+05:00
Google Colab crashes due to insufficient RAM (more than 12 GB is required) if resnet101 or resnet50 are used. Thus, resnet18 is used instead (approximately 6 GB is used).
diff --git a/beginner_source/introyt/captumyt.py b/beginner_source/introyt/captumyt.py
@@ -158,7 +158,7 @@
 # now.
 # 
 
-model = models.resnet101(weights='IMAGENET1K_V1')
+model = models.resnet18(weights='IMAGENET1K_V1')
 model = model.eval()
 
 

Original file line number	Diff line number	Diff line change
`@@ -158,7 +158,7 @@`
`158`	`158`	`# now.`
`159`	`159`	`#`
`160`	`160`
`161`		`-model = models.resnet101(weights='IMAGENET1K_V1')`
	`161`	`+model = models.resnet18(weights='IMAGENET1K_V1')`
`162`	`162`	`model = model.eval()`
`163`	`163`
`164`	`164`