First of all, thank the author for the excellent work.
I encountered the following error when trying to read pre-trained model information from themodels folder using tf.compat.v1.train.NewCheckpointReader("model_120.ckpt"). How can I solve this issue? (I'm sorry for asking such a silly question. I am a hardware learner and I want to deploy this model to an FPGA, but I lack sufficient learning experience in deep learning.)
Traceback (most recent call last):
File "C:\Users\lenovo\anaconda3\envs\tf\lib\site-packages\tensorflow\python\training\py_checkpoint_reader.py", line 92, in NewCheckpointReader
return CheckpointReader(compat.as_bytes(filepattern))
RuntimeError: Unable to open table file model_120.ckpt: DATA_LOSS: not an sstable (bad magic number): perhaps your file is in a different file format and you need to use a different restore operator?
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "readckpt.py", line 4, in <module>
NewCheck =tf.compat.v1.train.NewCheckpointReader("model_120.ckpt")
File "C:\Users\lenovo\anaconda3\envs\tf\lib\site-packages\tensorflow\python\training\py_checkpoint_reader.py", line 96, in NewCheckpointReader
error_translator(e)
File "C:\Users\lenovo\anaconda3\envs\tf\lib\site-packages\tensorflow\python\training\py_checkpoint_reader.py", line 40, in error_translator
raise errors_impl.DataLossError(None, None, error_message)
tensorflow.python.framework.errors_impl.DataLossError: Unable to open table file model_120.ckpt: DATA_LOSS: not an sstable (bad magic number): perhaps your file is in a different file format and you need to use a different restore operator?
First of all, thank the author for the excellent work. I encountered the following error when trying to read pre-trained model information from the
models
folder usingtf.compat.v1.train.NewCheckpointReader("model_120.ckpt")
. How can I solve this issue? (I'm sorry for asking such a silly question. I am a hardware learner and I want to deploy this model to an FPGA, but I lack sufficient learning experience in deep learning.)