cvalenzuela / scenescoop Goto Github PK

Hey did you use the Youtube-8M Dataset for training your model?

I tried to test the im2txt model but was stuck in executing the below command in the tutorial:

bazel-bin/im2txt/run_inference \ --checkpoint_path=${CHECKPOINT_DIR} \ --vocab_file=${VOCAB_FILE} \ --input_files=${IMAGE_FILE}

with the error showing that:

tensorflow.python.framework.errors_impl.NotFoundError: Tensor name "lstm/basic_lstm_cell/weights" not found in checkpoint files /home/ubuntu/im2txt/model.ckpt-3000000

This seems to be a mismatch problem between the checkpoint files and the tensorflow version. But I installed exactly the version in requirement.txt ( which is 1.1.0). And I downloaded exactly the same pretrained model in the link in README file.

when trying to run the server, i get:

Traceback (most recent call last):
  File "server.py", line 24, in <module>
    from credentials import account_sid, auth_token, number, movies
ImportError: cannot import name account_sid

pip install credentials is what i used to get this library down but that doesn't seem to fix it.

i got this to work, but a couple of minor path-oriented things were issues.

1. it crashes because the directory "temp" doesn't exist. making it manually fixes this.

2. had to change the paths in run_model.py to the im2txt checkpoint and vocab files because they were switched slightly recently: now models/research/im2txt instead of models/im2txt.

Regardless of whether I use the version of TF specified in requirements file or if I upgrade to 1.10.0 , I get the error regarding the checkpoint (running on my mac locally). Any ideas on using a different pre-trained model?

NotFoundError (see above for traceback): Restoring from checkpoint failed. This is most likely due to a Variable name or other graph key that is missing from the checkpoint. Please ensure that you have not altered the graph expected based on the checkpoint. Original error:

Tensor name "lstm/basic_lstm_cell/bias" not found in checkpoint files /Users/silverbox/Dropbox/video_manipulation/scenescoop/models/im2txt/checkpoints/model.ckpt-3000000
	 [[Node: save/RestoreV2 = RestoreV2[dtypes=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, ..., DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2/tensor_names, save/RestoreV2/shape_and_slices)]]