-
Notifications
You must be signed in to change notification settings - Fork 50
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Issue when running test.py with the provided checkpoint file #37
Comments
Dear xuchenwang, Can pls tell me from which link you have downloaded pre-trained checkpoint from the google drive |
Hi, Here is the link I downloaded the checkpoint, https://drive.google.com/drive/folders/1qeH5r5XEabkcQDJ25unSCvEUziRleN80 |
Hey thank you so much XuchechWang, I downloaded these file and added to checkpoints folder but still, I am getting an error I am trying to execute test.py but getting the following error. Restoring model from in test(options) /usr/local/lib/python3.6/dist-packages/tensorflow_core/python/training/saver.py in restore(self, sess, save_path) ValueError: The passed save_path is not a valid checkpoint: Could you please help me on these issues? |
Hi KPKWCE, Which save_path did you pass into the saver? My test.py also failed at this line, but with another bug, so I'm not sure if I can solve your problem. |
Hello XuchenWang, |
Hi XuchenWang, Same here! I get the following error: Any chance you can help with resolving it? Thanks in advance! |
I downloaded the pre-trained checkpoint from the google drive and changed 'init_from' to the address of .ckpt file. However, when I tried to run test.py, the got the following issue:
Restoring model from /data/congzou/xuchenwang/BidirectionalAttensiveFusion/final_results/model.ckpt Traceback (most recent call last): File "test.py", line 280, in <module> test(options) File "test.py", line 80, in test saver.restore(sess, options['init_from']) File "/data/congzou/xuchenwang/venv2.7t/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 1428, in restore {self.saver_def.filename_tensor_name: save_path}) File "/data/congzou/xuchenwang/venv2.7t/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 767, in run run_metadata_ptr) File "/data/congzou/xuchenwang/venv2.7t/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 965, in _run feed_dict_string, options, run_metadata) File "/data/congzou/xuchenwang/venv2.7t/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1015, in _do_run target_list, options, run_metadata) File "/data/congzou/xuchenwang/venv2.7t/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1035, in _do_call raise type(e)(node_def, op, message) tensorflow.python.framework.errors_impl. NotFoundError: Tensor name "caption_module/multi_rnn_cell/cell_1/lstm_cell/biases" not found in checkpoint files /data/congzou/xuchenwang/BidirectionalAttensiveFusion/final_results/model.ckpt [[Node: save/RestoreV2_12 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/RestoreV2_12/tensor_names, save/RestoreV2_12/shape_and_slices)]]
I notice that the .ckpt file does contain those kay values, so I wander what is going on with this bug? If possible, could you please provide a guide about loading pre-trained model?
The text was updated successfully, but these errors were encountered: