Gradients do not exist for variables

[CanshangD]

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

[MLForNerds]

Got the same issue, couldn't solve it. Kindly post the solution if you have solved it.

[IngLP]

I have the same issue and for me too the loss is NaN. Please help

[xiaolng]

same issue, loss becomes nan

[flori-shan]

same issue, please help

[jgarza9788]

can you please say what file you were running when you got this error? what version(s) of pytorch and python etc ?