EfficientDet.Pytorch icon indicating copy to clipboard operation
EfficientDet.Pytorch copied to clipboard

EfficientDet D0 weight SIZE is 40MB???

Open jduki opened this issue 4 years ago • 5 comments

As I read paper, efficient d0 size should be 3.8MB. Why d0 checkpoint weight included on git has 40MB size ??

jduki avatar Jan 18 '20 06:01 jduki

As I read paper, efficient d0 size should be 3.8MB. Why d0 checkpoint weight included on git has 40MB size ??

I guess 3.8M, which is 3.9M in the paper, is the number of parameters(see table 2...#Params),not the extact store space in the disk.

midasklr avatar Jan 19 '20 01:01 midasklr

As I read paper, efficient d0 size should be 3.8MB. Why d0 checkpoint weight included on git has 40MB size ??

I guess 3.8M, which is 3.9M in the paper, is the number of parameters(see table 2...#Params),not the extact store space in the disk.

Then, shouldn't it be around 16MB since the weights are in float32?

nsarang avatar Jan 23 '20 23:01 nsarang

As I read paper, efficient d0 size should be 3.8MB. Why d0 checkpoint weight included on git has 40MB size ??

I guess 3.8M, which is 3.9M in the paper, is the number of parameters(see table 2...#Params),not the extact store space in the disk.

Then, shouldn't it be around 16MB since the weights are in float32?

yes,u r right. the weight file is a orderdict include both weights and bias and other param names (orderdict keys)and their values(around 3.9m ).

midasklr avatar Jan 24 '20 12:01 midasklr

It is 40M because it stores the optimizer state during training in the weight file itself. Store only state dict to disk and you will get the exact weight.

dvlshah avatar Feb 02 '20 06:02 dvlshah

As I read paper, efficient d0 size should be 3.8MB. Why d0 checkpoint weight included on git has 40MB size ??

3.8M明显是参数的数量

guanshuicheng avatar Apr 03 '20 06:04 guanshuicheng