KGPML/Hyperspectral

ValueError: The passed save_path is not a valid checkpoint: model-spatial-11X11.ckpt-3999

juseph-dan opened this issue · 2 comments

juseph-dan commented

i am getting this error while runnig "Decoder_Spatial_CNN.py"

Sravani-Kalangi commented

check in your directory of how the file has been saved, for example in mine it has been saved as model-spatial-CNN-21x21.ckpt-3999 when i had patch size=21.

Linkersem commented

i have another question while running "CNN_feed.py“. when i set the patch size =7,it shows this:

File "C:\Users\Administrator\Desktop\test\CNN_G.py", line 257, in
run_training()
File "C:\Users\Administrator\Desktop\test\CNN_G.py", line 166, in run_training
loss = IndianPinesCNN.loss(logits, labels_placeholder)
File "C:\Users\Administrator\Desktop\test\IndianPinesCNN.py", line 135, in loss
labels=labels, logits=logits, name='xentropy')
File "E:\python3.5\lib\site-packages\tensorflow\python\ops\nn_ops.py", line 2653, in sparse_softmax_cross_entropy_with_logits
logits.get_shape()))
ValueError: Shape mismatch: The shape of labels (received (100,)) should equal the shape of logits except for the last dimension (received (400, 16))