relgukxilef / dense-depth-estimation Goto Github PK

when i run :python test.py , the error is next:

OMP: Info #250: KMP_AFFINITY: pid 27268 tid 28058 thread 57 bound to OS proc set 25
OMP: Info #250: KMP_AFFINITY: pid 27268 tid 28065 thread 64 bound to OS proc set 0
OMP: Info #250: KMP_AFFINITY: pid 27268 tid 28039 thread 38 bound to OS proc set 6
OMP: Info #250: KMP_AFFINITY: pid 27268 tid 28056 thread 55 bound to OS proc set 23
Traceback (most recent call last):
File "test.py", line 35, in
outputs = predict(model, inputs)
File "/home/wangwenzhong/project/lzq/DepthMap/dense-depth-estimation/DenseDepth-master/utils.py", line 10, in predict
predictions = model.predict(images, batch_size=batch_size)
File "/home/wangwenzhong/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training.py", line 908, in predict
use_multiprocessing=use_multiprocessing)
File "/home/wangwenzhong/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_arrays.py", line 723, in predict
callbacks=callbacks)
File "/home/wangwenzhong/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_arrays.py", line 394, in model_iteration
batch_outs = f(ins_batch)
File "/home/wangwenzhong/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/backend.py", line 3476, in call
run_metadata=self.run_metadata)
File "/home/wangwenzhong/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/client/session.py", line 1472, in call
run_metadata_ptr)
tensorflow.python.framework.errors_impl.InvalidArgumentError: input and filter must have the same depth: 1664 vs 1
[[{{node conv2/BiasAdd}}]]

I don't know what is question ? about "input and filter must have the same depth: 1664 vs 1
[[{{node conv2/BiasAdd}}]]"