Runtime error while testing

Hello,

I am getting the following error every time i am trying to run one of the command in testing:-

python main.py --task=test --subtask=ori --logdir=logs/test --test_img_file=image1.jpg --test_out_file=image1_ori.txt --test_kp_file=image1_kp.txt --use_batch_norm=False
/home/user/anaconda2/envs/tf/lib/python3.5/site-packages/h5py/init.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.
from ._conv import register_converters as _register_converters
User and hostname: user@8RM7KY3
2018-07-06 18:54:33.866125: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX
-- Using default values for mean/std

Variables: name (type shape) [size]

network/lift/ori/conv-act-pool-1/weights:0 (float32_ref 5x5x1x10) [250, bytes: 1000]
network/lift/ori/conv-act-pool-1/biases:0 (float32_ref 10) [10, bytes: 40]
network/lift/ori/conv-act-pool-2/weights:0 (float32_ref 5x5x10x20) [5000, bytes: 20000]
network/lift/ori/conv-act-pool-2/biases:0 (float32_ref 20) [20, bytes: 80]
network/lift/ori/conv-act-pool-3/weights:0 (float32_ref 3x3x20x50) [9000, bytes: 36000]
network/lift/ori/conv-act-pool-3/biases:0 (float32_ref 50) [50, bytes: 200]
network/lift/ori/fc-ghh-drop-4/weights:0 (float32_ref 1250x1600) [2000000, bytes: 8000000]
network/lift/ori/fc-ghh-drop-4/biases:0 (float32_ref 1600) [1600, bytes: 6400]
network/lift/ori/fc-ghh-5/weights:0 (float32_ref 100x32) [3200, bytes: 12800]
network/lift/ori/fc-ghh-5/biases:0 (float32_ref 32) [32, bytes: 128]
network/lift/desc/conv-act-pool-norm-1/weights:0 (float32_ref 7x7x1x32) [1568, bytes: 6272]
network/lift/desc/conv-act-pool-norm-1/biases:0 (float32_ref 32) [32, bytes: 128]
network/lift/desc/conv-act-pool-norm-2/weights:0 (float32_ref 6x6x32x64) [73728, bytes: 294912]
network/lift/desc/conv-act-pool-norm-2/biases:0 (float32_ref 64) [64, bytes: 256]
network/lift/desc/conv-act-pool-3/weights:0 (float32_ref 5x5x64x128) [204800, bytes: 819200]
network/lift/desc/conv-act-pool-3/biases:0 (float32_ref 128) [128, bytes: 512]
Total size of variables: 2299482
Total bytes of variables: 9197928

Loading Trained Network

[joint] Checking if old pre-trained weights exists in
[joint] No pretrained weights from the old framework
[joint] Checking if previous Tensorflow run exists in
[joint] No previous Tensorflow result
[joint] Checking if previous Tensorflow run exists in logs/test/joint
[joint] No previous Tensorflow result
[ori] Checking if old pre-trained weights exists in
[ori] No pretrained weights from the old framework
[ori] Checking if previous Tensorflow run exists in
[ori] No previous Tensorflow result
[ori] Checking if previous Tensorflow run exists in logs/test/ori
[ori] No previous Tensorflow result
Traceback (most recent call last):
File "main.py", line 98, in
tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)
File "/home/user/anaconda2/envs/tf/lib/python3.5/site-packages/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "main.py", line 70, in main
task.run()
File "/media/user/SSD-0/Linux/Projects/TF_LIFT/tf-lift-master/tester.py", line 110, in run
raise RuntimeError("Could not load network weights!")
RuntimeError: Could not load network weights!

I am using Tensorflor 1.4, Cuda 8, opencv3.4. tensorboard 0.4. Any suggestions to resolve this error, will be very helpful.

Thanks in advance.

Hi,

it's telling you that it cannot load weights? So probably you want to check if the paths are correct?

Cheers

I am running the command where main.py is located. The command for testing, i am trying is :-
python main.py --task=test --subtask=kp --logdir=logs/test --test_img_file=image1.jpg
--test_out_file=image1_kp.txt

You probably want to remove the try catch surrounding the restore_network and see why the restoration is failing.

Hi, I have exactly the same problem here.

I am confused about "remove the try catch surrounding the restore_network" ? I have deleted all
pycache and try again. Still it has the same problem.

The path of main.py and image1.jpg are all correct. Could you please help with this problem? Thanks so much.

I have same problem with you. I even create some file folders such as log. But the problem still exist

Hi Guys, I'm traveling at the moment. You can debug this your selves by removing the

tf-lift/tester.py

Line 103 in 5530e47

try:

try except here and then diving into where the crash exactly happened.

Closed due to no further activity