Pre trained model

[shivammalviya712]

Hi @TianzhongSong,

When I am loading the pre-trained weights into the model present in model_cls.py, it's showing an error that they have a different number of layers. Can you please help?

Thank you in advance (^_^)

Error:

(pointnet_tf2) shivam@Jarvis:~/catkin_ws/src/pointnet_tf2/src$ /home/shivam/anaconda3/envs/pointnet_tf2/bin/python /home/shivam/catkin_ws/src/PointNet-Keras/lab.py
2021-01-02 10:08:07.776251: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'libcuda.so.1'; dlerror: libcuda.so.1: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /home/shivam/catkin_ws/devel/lib:/opt/ros/melodic/lib
2021-01-02 10:08:07.776298: E tensorflow/stream_executor/cuda/cuda_driver.cc:313] failed call to cuInit: UNKNOWN ERROR (303)
2021-01-02 10:08:07.776343: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:156] kernel driver does not appear to be running on this host (Jarvis): /proc/driver/nvidia/version does not exist
2021-01-02 10:08:07.776675: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
2021-01-02 10:08:07.809391: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 2699905000 Hz
2021-01-02 10:08:07.809883: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f6d80000b20 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2021-01-02 10:08:07.809951: I tensorflow/compiler/xla/service/service.cc:176]   StreamExecutor device (0): Host, Default Version
Traceback (most recent call last):
  File "/home/shivam/catkin_ws/src/PointNet-Keras/lab.py", line 6, in <module>
    model.load_weights('/home/shivam/catkin_ws/src/PointNet-Keras/results/pointnet.h5')
  File "/home/shivam/anaconda3/envs/pointnet_tf2/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py", line 250, in load_weights
    return super(Model, self).load_weights(filepath, by_name, skip_mismatch)
  File "/home/shivam/anaconda3/envs/pointnet_tf2/lib/python3.6/site-packages/tensorflow/python/keras/engine/network.py", line 1266, in load_weights
    hdf5_format.load_weights_from_hdf5_group(f, self.layers)
  File "/home/shivam/anaconda3/envs/pointnet_tf2/lib/python3.6/site-packages/tensorflow/python/keras/saving/hdf5_format.py", line 685, in load_weights_from_hdf5_group
    ' layers.')
ValueError: You are trying to load a weight file containing 19 layers into a model with 37 layers.

[ohadlights]

Same here. TF 2.4.1