https://github.com/jav0927/course-v3/blob/master/Fastai2_SSD_Model.ipynb def model_split(m): return L(m.body[0], m.body[1], m.body[2], m.body[3], m.body[4], m.body[5], m.body[6], m.body[7], m.drop).map(params)

epoch train_loss valid_loss time
0 48.916576 47.567001 00:55
1 48.897285 47.704815 00:54
2 48.736855 47.622379 00:54

if I change model_split as follows:

`def model_split(m): body_params, head_params = L(),L()

body_params = L(m.body[0], m.body[1], m.body[2], m.body[3], m.body[4], m.body[5], m.body[6], m.body[7], m.drop).map(params)

# head_params = L(m.sconv0, m.sconv1, m.sconv2, m.sconv3, m.out0, m.out1, m.out2, m.out3).map(params)
for p in m.body:
    body_params += params(p)
head_params += params(m.sconv0)
head_params += params(m.sconv1)
head_params += params(m.sconv2)
head_params += params(m.sconv3)
head_params += params(m.out0)
head_params += params(m.out1)
head_params += params(m.out2)
head_params += params(m.out3)
return L(body_params, head_params)`

Then, loss like:

I think probably this is a problem

fastai / course-v3

model_split seems a little problem. Adam cannot get head_params, and cannot update head params! #598

body_params = L(m.body[0], m.body[1], m.body[2], m.body[3], m.body[4], m.body[5], m.body[6], m.body[7], m.drop).map(params)