search

rohanchandra30 / TrackNPred

This is the code base for our ACM CSCS 2019 paper: "RobustTP: End-to-End Trajectory Prediction for Heterogeneous Road-Agents in Dense Traffic with Noisy Sensor Inputs". This codebase contains implementations for several trajectory prediction methods including Social-GAN and TraPHic.
https://arxiv.org/pdf/1907.08752.pdf
199 stars 63 forks source link

Issue in tracking #6

Closed rabiaali95 closed 5 years ago

rabiaali95 commented 5 years ago

I ran detection and tracking from scratch for TRAF13 dataset. Detection is done successfully but for tracking i am facing with the following error. Can you please guide how to get rid of this

finished detection for resources/data/TRAFF/TRAF13... begin tracking for resources/data/TRAFF/TRAF13... TRAF13 Processing TRAF13 2019-08-30 13:28:03.614975: W tensorflow/compiler/jit/mark_for_compilation_pass.cc:1412] (One-time warning): Not using XLA:CPU for cluster because envvar TF_XLA_FLAGS=--tf_xla_cpu_global_jit was not set. If you want XLA:CPU, either set that envvar, or use experimental_jit_scope to enable XLA:CPU. To confirm that XLA is active, pass --vmodule=xla_compilation_cache=1 (as a proper command-line flag, not via TF_XLA_FLAGS) or set the envvar XLA_FLAGS=--xla_hlo_profile. DATASET densepeds: resources/data/TRAFF Traceback (most recent call last): File "main_cmd.py", line 109, in model.tracking(args.dir, DATA_FOLDER.format(i), False) File "/hdd/local/sda/rabia/TrackNPred/model/model.py", line 130, in tracking densepeds(dataDir, data_folder, display, thread) File "/hdd/local/sda/rabia/TrackNPred/model/Tracking/DensePeds.py", line 304, in densepeds run(sequence_dir, detection_file, output_file, matlab_file, min_conf, nms, min_det_ht, max_cos_dist, nn_budget, disp, thread) File "/hdd/local/sda/rabia/TrackNPred/model/Tracking/DensePeds.py", line 227, in run visualizer.run(frame_callback, thread) TypeError: run() takes 2 positional arguments but 3 were given (trackNpred) rabia@vivace-server:~/TrackNPred$

rabiaali95 commented 5 years ago

Also if i use the provided tracking then there is an error in generating formatted txt. The error is as follows begin tracking for resources/data/TRAFF/TRAF13... DATASET densepeds: resources/data/TRAFF TRAF13 0.014071941375732422 finished tracking for resources/data/TRAFF/TRAF13... Formatting resources/data/TRAFF/TRAF13 for prediction... /hdd/local/sda/rabia/TrackNPred/model/Tracking/hypo_formatter.py:46: UserWarning: loadtxt: Empty input file: "<_io.TextIOWrapper name='resources/data/TRAFF/TRAF13/hypotheses.txt' mode='r' encoding='UTF-8'>" hypo_mtrx = np.loadtxt(f, delimiter=',') Traceback (most recent call last): File "main_cmd.py", line 123, in formatFile(hypo, i, formatted_hypo) File "/hdd/local/sda/rabia/TrackNPred/model/Tracking/hypo_formatter.py", line 52, in formatFile formatted = getFormattedDF(inFilePath, dsetID) File "/hdd/local/sda/rabia/TrackNPred/model/Tracking/hypo_formatter.py", line 48, in getFormattedDF return formatHypo(dsetID, hypo_mtrx) File "/hdd/local/sda/rabia/TrackNPred/model/Tracking/hypo_formatter.py", line 34, in formatHypo formatted_df['vid_idx'] = list(hypo_mtrx[:,HYP_VID_IDX].astype(int)) IndexError: too many indices for array

How to solve this as well?

rohanchandra30 commented 5 years ago

Thanks, we will get to this soon.

rayguan97 commented 5 years ago

Now this issue is fixed.