Closed stevewells20 closed 6 years ago
It’s looking for the model checkpoint that you downloaded from the model zoo. You should move the files to the root directory of the repo and the path in the config should just be “model.ckpt” and it should work
Ah I see, I unpacked all of the files to the model directory, rather than splitting them between model and rootdir. The tensorflow bug with identical error messages threw me off... Thank you for the quick response! Closing as user error.
The files I have after unpacking the faster_rcnn_resnet101_coco are model.ckpt.index and model.ckpt.meta and mdoel.ckpt.data-00000-of-00001. Should I be deleting the extensions?
I'm on Arch, so there could be any number of crazy problems. Followed all install instructions; while running train.py I receive: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for model.ckpt There is a tensorflow issue currently open regarding naming conventions, but even using the full path for all of the files I still get the same error. Any ideas?