Issue when running test.py with the provided checkpoint file

[XuchenWang]

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?

[KPKWCE]

Dear xuchenwang,

Can pls tell me from which link you have downloaded pre-trained checkpoint from the google drive

[XuchenWang]

Hi,

Here is the link I downloaded the checkpoint, https://drive.google.com/drive/folders/1qeH5r5XEabkcQDJ25unSCvEUziRleN80

[KPKWCE]

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 ValueError Traceback (most recent call last) in 3 tf.reset_default_graph() 4 options = default_options() ----> 5 test(options)

in test(options) 20 print('Restoring model from %s'%options['init_from']) 21 saver = tf.train.Saver() ---> 22 saver.restore(sess, options['init_from']) 23 24 word2ix = options['vocab']

/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/training/saver.py in restore(self, sess, save_path) 1280 if not checkpoint_management.checkpoint_exists_internal(checkpoint_prefix): 1281 raise ValueError("The passed save_path is not a valid checkpoint: " + -> 1282 checkpoint_prefix) 1283 1284 logging.info("Restoring parameters from %s", checkpoint_prefix)

ValueError: The passed save_path is not a valid checkpoint:

Could you please help me on these issues? Thanks for your time and great work!

[XuchenWang]

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.

[KPKWCE]

Hello XuchenWang, Actually I'm directly trying to run test.py , but in the checkpoint folder, there was no any epoch file so getting an error. So first i trained with train.py but only generated the following file No epoch file. status and event file.... Pls help for this why epoch file is not genrated

[galrapo]

Hi XuchenWang,

Same here!

I get the following error: NotFoundError (see above for traceback): Tensor name "caption_module/multi_rnn_cell/cell_1/lstm_cell/weights" not found in checkpoint files checkpoints/model.ckpt

Any chance you can help with resolving it?

Thanks in advance!