Closed chriszhenghaochen closed 6 years ago
I modify for reading bugs for tensorflow, but I don't think they should be relevant
checkpoint_dir = os.path.dirname(args.model)
ckpt = tf.train.get_checkpoint_state(checkpoint_dir)
if ckpt and ckpt.model_checkpoint_path:
print('FOUND')
saver.restore(sess, ckpt.model_checkpoint_path)
else:
print('NOT FOUND')
print ('Loading model weights from {:s}').format(args.model)
Problem solved, it due to my own path issue :p with VOC0712 directory, the result was now produced
Hello. Recently I am try to understand FPN, and would you share how can I get voc0712 dataset correctly?
Hi, I used your shared ckpt file to test the validation and run with VOC07 + 12 but get all -1 for mAP, (also try 07 but get the same result :( ) @xmyqsh
I am wondering anyone has any ideas about this error?