LightCTR icon indicating copy to clipboard operation
LightCTR copied to clipboard

xDeepfm can't save model

Open RisanLi opened this issue 5 years ago • 0 comments

If I code 'model.save_weights(...)' after model.fit in xDeepfm, then i get the traceback:

Traceback (most recent call last): File "train_xdeepfm.py", line 74, in model.save_weights('weights/test.h5') File "/home/lixiang/anaconda3/envs/env_tf2/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/network.py", line 1074, in save_weights saving.save_weights_to_hdf5_group(f, self.layers) File "/home/lixiang/anaconda3/envs/env_tf2/lib/python3.6/site-packages/tensorflow_core/python/keras/saving/hdf5_format.py", line 631, in save_weights_to_hdf5_group param_dset = g.create_dataset(name, val.shape, dtype=val.dtype) File "/home/lixiang/anaconda3/envs/env_tf2/lib/python3.6/site-packages/h5py/_hl/group.py", line 139, in create_dataset self[name] = dset File "/home/lixiang/anaconda3/envs/env_tf2/lib/python3.6/site-packages/h5py/_hl/group.py", line 373, in setitem h5o.link(obj.id, self.id, name, lcpl=lcpl, lapl=self._lapl) File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper File "h5py/h5o.pyx", line 202, in h5py.h5o.link RuntimeError: Unable to create link (name already exists)

However i changed model from xdeepfm to deepfm, model.save_weights() ran successfully. Whats wrong with the xdeepfm ?

thanks.

RisanLi avatar Mar 06 '20 08:03 RisanLi