Skip to content
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

detect nothing #80

Open
wengjinfang opened this issue Aug 15, 2018 · 2 comments
Open

detect nothing #80

wengjinfang opened this issue Aug 15, 2018 · 2 comments

Comments

@wengjinfang
Copy link

WEIGHTS_FILE = None,then train a very big iters,loss still be around 10,and detect nothing,whats problem

@cenwfohdkue
Copy link

cenwfohdkue commented Oct 4, 2018

you need use their pre-training file YOLO_small.ckpt, then it works. Otherwise the LOSS will be very big.
#WEIGHTS_FILE = None
WEIGHTS_FILE = os.path.join(DATA_PATH, 'weights', 'YOLO_small.ckpt')

@JokerKangS
Copy link

you need use their pre-training file YOLO_small.ckpt, then it works. Otherwise the LOSS will be very big.
#WEIGHTS_FILE = None
WEIGHTS_FILE = os.path.join(DATA_PATH, 'weights', 'YOLO_small.ckpt')

if i want to change the net, such as change the cell_size, it won't work when i use yolo_small.ckpt. so, what should i do if i want to train the net from zero?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants