tccoin/image-based-indoor-localization

An image-based localization framework based on work of Song et al, featuring hardware-accelerated image searching​ and optimization with GTSAM.

Hi there 👋

• 🔭 Currently PhD Student in Computational Autonomy and Robotics Laboratory (CURLY) at University of Michigan.
• 🦿 Previously worked in RoboVigor Robotics Team.
• 📫 Feel free to visit Klog!

image-based-indoor-localization's Issues

error: namespace "thrust" has no member "min_element" during the "Compile fast searching module" step

I met an issues described in attached picture during the step "Compile fast searching module". My gcc and cuda version are shown in the picture as well. I changed cmakelist.txt a little bit(change 20 to 14) because there is an error "invalid value 20". Could you help me to find the problem?

breakdown when try to train the network

When I am on the fourth step:Train the model and run python image_based_localization/siamese_network/train.py
The program met a breakdown. errors are shown as below: The full errors can be seen in the picture

WARNING:tensorflow:AutoGraph could not transform <function parse_function at 0x7f80c8fc8a60> and will run it as-is.
Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output.
Cause: module 'gast' has no attribute 'Index'
To silence this warning, decorate the function with @tf.autograph.experimental.do_not_convert
2023-03-16 19:38:42.859210: I tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:116] None of the MLIR optimization passes are enabled (registered 2)
2023-03-16 19:38:42.880150: I tensorflow/core/platform/profile_utils/cpu_utils.cc:112] CPU Frequency: 2599990000 Hz
Traceback (most recent call last):
File "/home/shen/UM-MS-study/ROB530/image-based-indoor-localization/image_based_localization/siamese_network/train.py", line 387, in
train.train()
File "/home/shen/UM-MS-study/ROB530/image-based-indoor-localization/image_based_localization/siamese_network/train.py", line 273, in train
te_pairs, te_y = self.valid_pairs_generator(
File "/home/shen/UM-MS-study/ROB530/image-based-indoor-localization/image_based_localization/siamese_network/train.py", line 152, in valid_pairs_generator
i = random.randrange(0, num_data - 1)
File "/home/shen/anaconda3/envs/tf/lib/python3.9/random.py", line 316, in randrange
raise ValueError("empty range for randrange() (%d, %d, %d)" % (istart, istop, width))
ValueError: empty range for randrange() (0, -1, -1)