You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I am having this error in C3D " video_data_layer.cpp:308] failed to read chunk list " when I execute the .sh file for training. Here are the things I have done:
--> My trrain_classify_ucf101.sh file is pointing to /tools/train_net.bin and solver_classify_ucf101.protoxt. I assume that I don't have to do anything with the train_net.bin file, whereas the solver file is in the same folder as .sh file
--> The solver file is correctly pointing to the train_classify_ucf101.prototxt
--> The train_classify_ucf101.prototxt file is correctly pointing to the path of the train01.lst i.e. "../../data/classification/images/train01.lst"
--> The "train01.lst" file is correctly pointing to the path of images (named in %06d format)
Any hints or pointers will be highly appreciated - i am stuck in this for many days.
Many thanks
FB
Please use the caffe-users list for usage, installation, or modeling questions, or other requests for help. Do not post such requests to Issues. Doing so interferes with the development of Caffe.
If you are having difficulty building Caffe or training a model, please ask the caffe-users mailing list. If you are reporting a build error that seems to be due to a bug in Caffe, please attach your build configuration (either Makefile.config or CMakeCache.txt) and the output of the make (or cmake) command.
Your system configuration
Operating system:
Compiler:
CUDA version (if applicable):
CUDNN version (if applicable):
BLAS:
Python or MATLAB version (for pycaffe and matcaffe respectively):
The text was updated successfully, but these errors were encountered:
Dear chuckcho - yes the path is absolute. And it is able to read the videos now I1121 06:32:51.941296 29689 video_data_layer.cpp:317] A total of 8 video chunks.
I am having this error in C3D " video_data_layer.cpp:308] failed to read chunk list " when I execute the .sh file for training. Here are the things I have done:
--> My trrain_classify_ucf101.sh file is pointing to /tools/train_net.bin and solver_classify_ucf101.protoxt. I assume that I don't have to do anything with the train_net.bin file, whereas the solver file is in the same folder as .sh file
--> The solver file is correctly pointing to the train_classify_ucf101.prototxt
--> The train_classify_ucf101.prototxt file is correctly pointing to the path of the train01.lst i.e. "../../data/classification/images/train01.lst"
--> The "train01.lst" file is correctly pointing to the path of images (named in %06d format)
Any hints or pointers will be highly appreciated - i am stuck in this for many days.
Many thanks
FB
Please use the caffe-users list for usage, installation, or modeling questions, or other requests for help.
Do not post such requests to Issues. Doing so interferes with the development of Caffe.
Please read the guidelines for contributing before submitting this issue.
Issue summary
Steps to reproduce
If you are having difficulty building Caffe or training a model, please ask the caffe-users mailing list. If you are reporting a build error that seems to be due to a bug in Caffe, please attach your build configuration (either Makefile.config or CMakeCache.txt) and the output of the make (or cmake) command.
Your system configuration
Operating system:
Compiler:
CUDA version (if applicable):
CUDNN version (if applicable):
BLAS:
Python or MATLAB version (for pycaffe and matcaffe respectively):
The text was updated successfully, but these errors were encountered: