kujason/avod

Issues

• Evaluate the mAP of only one image

  #204 opened 8 months ago by MCUBE-2023
  0

• Here is a non-commercial Wechat group for discussing the lidar-based perception technologies. Welcome to join us.

  #159 opened 5 years ago by deepmeng
  7

• request to give access for pretrained model

  #203 opened a year ago by srushti1763
  0

• could anyone send me a Pretrained model for SSD-AVOD / AVOD ?

  #202 opened a year ago by Jesser1855
  1

• How to evaluate the module on testing set?

  #175 opened 4 years ago by 619862306
  1

• protoc: not found

  #201 opened 2 years ago by vehicle-jyw
  1

• No checkpoints found

  #164 opened 4 years ago by DavidDiosdado
  5

• Excuse me, an error is reported when generating Mini-batch, for obj_label in obj_labels: TypeError: 'NoneType' object is not iterable. What is the reason for this?

  #199 opened 2 years ago by duuxu
  0

• Model capability to work with a tilted camera frame

  #198 opened 2 years ago by srimannarayanabaratam
  1

• Pretrained Model

  #192 opened 3 years ago by jianghy1998
  1

• Run pretrained model

  #155 opened 5 years ago by Subhankar48
  11

• About the RPN loss (smooth_L1_LOSS)

  #197 opened 3 years ago by hehualin-tut
  0

• Result of test set

  #196 opened 3 years ago by qiaoli96
  0

• questions about usage of kitti(more specifically which files to download)?

  #194 opened 3 years ago by sparshgarg23
  1

• Problems with Run Evaluator

  #193 opened 3 years ago by qiaoli96
  0

• Checking the mAP for cars, cyclist, and pedestrian

  #183 opened 4 years ago by shaunkheng97
  9

• TypeError: build() got multiple values for argument 'layers_config'

  #191 opened 3 years ago by RMobina
  2

• Convert checkpoints to frozen graph, "ValueError: graph_def is invalid at node u'global_step/Assign': Input tensor 'global_step:0' Cannot convert a tensor of type int32 to an input of type int32_ref."

  #190 opened 3 years ago by yukaryote
  0

• What is the difference between box_3d , 'box_8c', 'box_8co',box_4c,'box_4ca' encoding for a bounding box ??

  #189 opened 3 years ago by vignesh628
  4

• ImportError: cannot import name 'kitti_dataset_pb2' from 'avod.protos'

  #187 opened 4 years ago by bm-93
  1

• What is the meaing of each value of output file?

  #188 opened 4 years ago by Haawron
  1

• ImportError: No module named 'wavedata.tools'

  #185 opened 4 years ago by arxidinakbar
  1

• Running in real time

  #186 opened 4 years ago by Soumyad25
  0

• Running AVOD on Jetson Xavier

  #184 opened 4 years ago by shaunkheng97
  0

• Difference between AP3D and AP BEV ?

  #182 opened 4 years ago by Laihu08
  0

• How to colorize the point cloud ?

  #181 opened 4 years ago by Laihu08
  1

• Error during evaluation

  #180 opened 4 years ago by Pari-singh
  1

• confused: different image scales, if all images resized to the same scale,what about the gt bbox in image?

  #179 opened 4 years ago by liyang0522
  3

• custom train-val split and ground planes for test set

  #153 opened 4 years ago by mrshim1101
  1

• Inference Speed

  #174 opened 4 years ago by linchunmian
  1

• Issues with Evaluation Script

  #169 opened 4 years ago by jmiemirza
  2

• conflict on evaluation of checkpoints

  #166 opened 4 years ago by RMobina
  1

• What are the planes *.bin files?

  #154 opened 4 years ago by FranciscoGomez90
  2

• tensorflow version

  #172 opened 4 years ago by Leo-godel
  1

• evaluate question

  #156 opened 4 years ago by Buerzhu
  1

• Is it possible to use with ROS and latest CUDA 10 and cuddn 7.1?

  #171 opened 4 years ago by astronaut71
  1

• fakepath error when trying to visualize results

  #167 opened 5 years ago by sarimmehdi
  1

• confused about the aug method

  #176 opened 4 years ago by liyang0522
  2

• No checkpoint found when doing inference

  #165 opened 4 years ago by sarimmehdi
  1

• Can you tell me your configuration when you train the avod code ? My computer reboot when I train it in my GPU

  #161 opened 4 years ago by daodaoling
  5

• ImportError: No module named avod

  #160 opened 4 years ago by chrisyan
  1

• multi_class train on this model

  #158 opened 4 years ago by Jiachenyin1
  2

• I am unable to clone the repository .. why?

  #173 opened 4 years ago by MohamedAboushnief
  5

• __init__() got an unexpected keyword argument 'serialized_options'

  #178 opened 4 years ago by shaunkheng97
  1

• variation of the number of clusters doesn't work

  #177 opened 4 years ago by patelrahil224
  0

• pre-trained model availability

  #170 opened 5 years ago by dmatos2012
  2

• kitti_bev_vis.py

  #168 opened 5 years ago by RohDonghyeon
  0

• Wierd thing! The same input data, different anchors?

  #163 opened 5 years ago by NoRomantic
  2

• How to compile twice?

  #162 opened 5 years ago by NoRomantic
  2

• You need to create a preprocessing config, such as those in mb_preprocessing that includes the classes Car Pedestrian and Cyclist. After that you need to set up preprocessing in gen_mini_batches.py to process All using the config you set up. If you want more classes you will at least also have to modify kitti_dataset.py as it is hardcoded to name joint detection of Pedestrian and Cyclist as 'People' and Pedestrian, Cyclist and Car as 'All', but I haven't tested expanding this yet.

  #157 opened 5 years ago by Jiachenyin1
  0