-
Notifications
You must be signed in to change notification settings - Fork 2.9k
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.
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
Refine network config for MobileNet-SSD. #721
Conversation
batch_size, | ||
num_passes, | ||
model_save_dir='model', | ||
init_model_path=None): |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
好像没有地方用到这个选项?
gt_label, | ||
gt_box, | ||
difficult, | ||
21, |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
'class_num' should be defined as a variable to avoid magic number.
staircase=True), | ||
regularization=fluid.regularizer.L2Decay(0.0005), ) | ||
|
||
opts = optimizer.minimize(loss) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
It seems that 'opts' is not necessary.
fetch_list=[accum_map]) | ||
print("Test {0}, map {1}".format(pass_id, test_map[0])) | ||
|
||
#print fluid.default_main_program() |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Remove this comments?
@@ -35,5 +36,32 @@ def load_and_set_vars(place): | |||
t.set(v, place) | |||
|
|||
|
|||
# From Paddle V1 | |||
def load_paddlev1_vars(place): |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
load_paddlev1_vars
、 load_and_set_vars
和load_vars
这三个方法的名称和关系有待优化一下。
@wanghaoshuang Thanks! I will fix them in next PR. |
No description provided.