You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I got the following error when running in test mode with this command 'return tf.cond(is_train, train, val)'
ValueError: Cannot reshape a tensor with 4320000 elements to shape [1,160,60,3](28800 elements) for 'cond/reshape' (op:'Reshape') with input shapes:[1,150,160,60,3],[4] and .........
Not sure how to overcome it. Appreciate if you can take a look at this issue.
BTW, the paper indicated a CMC rank 1 of 50.19% for CUHK03 dataset. I got 87.7% accuracy from validation run. Does it imply your implementation has much better performance? If yes, what are the possible reasons?
Thanks
The text was updated successfully, but these errors were encountered:
I got the following error when running in test mode with this command 'return tf.cond(is_train, train, val)'
ValueError: Cannot reshape a tensor with 4320000 elements to shape [1,160,60,3](28800 elements) for 'cond/reshape' (op:'Reshape') with input shapes:[1,150,160,60,3],[4] and .........
Not sure how to overcome it. Appreciate if you can take a look at this issue.
BTW, the paper indicated a CMC rank 1 of 50.19% for CUHK03 dataset. I got 87.7% accuracy from validation run. Does it imply your implementation has much better performance? If yes, what are the possible reasons?
Thanks
The text was updated successfully, but these errors were encountered: