Open CanshangD opened 4 years ago
Got the same issue, couldn't solve it. Kindly post the solution if you have solved it.
I have the same issue and for me too the loss is NaN. Please help
same issue, loss becomes nan
same issue, please help
can you please say what file you were running when you got this error? what version(s) of pytorch and python etc ?
I have got the error “Gradients do not exist for variables” when training faster rcnn, and the loss is nan.
log: W1108 09:59:39.735346 139647501481728 optimizer_v2.py:1029] Gradients do not exist for variables ['faster_rcnn/b_box_head/rcnn_class_conv1/kernel:0', 'faster_rcnn/b_box_head/rcnn_class_conv1/bias:0', 'faster_rcnn/b_box_head/rcnn_class_bn1/gamma:0', 'faster_rcnn/b_box_head/rcnn_class_bn1/beta:0', 'faster_rcnn/b_box_head/rcnn_class_conv2/kernel:0', 'faster_rcnn/b_box_head/rcnn_class_conv2/bias:0', 'faster_rcnn/b_box_head/rcnn_class_bn2/gamma:0', 'faster_rcnn/b_box_head/rcnn_class_bn2/beta:0', 'faster_rcnn/b_box_head/rcnn_class_logits/kernel:0', 'faster_rcnn/b_box_head/rcnn_class_logits/bias:0', 'faster_rcnn/b_box_head/rcnn_bbox_fc/kernel:0', 'faster_rcnn/b_box_head/rcnn_bbox_fc/bias:0'] when minimizing the loss. epoch 0 2 nan