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鈥檒l occasionally send you account related emails.
Already on GitHub? Sign in to your account
Various questions #13
Comments
Thank you for your attention, @abagshaw! Basically, the model functions always return
from tensornets.utils import set_args
from tensornets.utils import var_scope
opts = nets.references.yolo_utils.opts('yolov2voc')
opts['classes'] = 545
@var_scope('yolov2')
@set_args(nets.references.yolos.__args__)
def yolov2_for_you(x, is_training=False, scope=None, reuse=None):
def _get_boxes(*args, **kwargs):
return nets.references.yolo_utils.get_v2_boxes(opts, *args, **kwargs)
x = nets.references.yolos.yolo(x, [1, 1, 3, 3, 5, 5], 125, is_training, scope, reuse)
x.get_boxes = _get_boxes
return x
np.save('your_weights', sess.run(model.get_weights())) # save
sess.run([w.assign(v) for (w, v) in zip(model.get_weights(), np.load('your_weights.npz'))]) # load
train_list = model.get_weights()[6:] # The first six weights are not going to be updated.
train = tf.train.AdamOptimizer().minimize(loss, var_list=train_list)
|
@taehoonlee Thanks for the super quick response!
I'll certainly see if I can get training up and running on a TPU when I have a chance after the loss function is implemented. Thanks again for all your work on this! |
You are right @abagshaw, |
@abagshaw, Please see #14 for the FP16 supports. The native operations support the FP16 since |
@taehoonlee Awesome, thanks! Also, no pressure - but any progress on YOLO training? 馃槂 |
@abagshaw, Almost finished 馃敟. |
@abagshaw, I wrote and tested training codes based on darknet and darkflow, but learning did not progress at 5% mAP. Thus, I added a draft version first and will revise it with pytorch implementation. Would you have the bandwidth to review the draft, @abagshaw? I would appreciate if you could find any reasons for poor convergence 馃槶. |
@taehoonlee Awesome, thanks so much! Right now I'm swamped with work so I don't see myself getting time to tinker around with it - but if a break comes up I'll certainly give it a shot. |
First off, thanks very much for all your work on this - a really clean and understandable implementation of YOLO 馃槃 I have a few questions (probably very basic) about getting started with training and inference with tensornets - in specific to the YOLOv2 model:
stopbackward=1
?Thanks very much!
The text was updated successfully, but these errors were encountered: