ApoorvaSuresh

Results 8 comments of ApoorvaSuresh

After starting training the model,it doesn't work and only see "learning rate 0.0002000 -> 0.0002000"

@simon-eda hey, did you find out what has to be changed to make it work? Please let me know :) Thank you!

RuntimeError: max(): Expected reduction dim to be specified for input.numel() == 0. In tools/test.py

Hi, I have the same error :( Did you find a solution for it? If so, could you please share it? Thanks in advance :)

Layer #389 (named "mrcnn_bbox_fc"), weight <tf.Variable 'mrcnn_bbox_fc/kernel:0' shape=(1024, 8) dtype=float32_ref> has shape (1024, 8), but the saved weight has shape (1024, 324)

I get the same error while training it. Has anyone resolved this issue?

Sanity Check failure

What is the difference between COCO's AP (at iou = 0.5) and Kitti's 2D AP when I set iou to 0.5? Why do I always get very different values?

Segmentation fault Error.

@lonely7yk @17824823008 Doesn't work for me :( do you know of any other stuff to try?

Criteria for filtering detections

Hi, I would expect the 2D AP to be somewhat close to the value I get when I evaluate it with COCO evaluation script. Kitti 2D (iou=0.5) AP: 35.7, 32.3,...

use centerpoint to process my customized dataset

Hi :) have you figured this out? Please let me know. Thank you in advance!

Extract features from various layers of MaskRCNN, such as ROI align features, pyramid features [P1,P2,P3,P4,P5]

Hi, @SwetaKaman @VellalaVineethKumar were you successful in doing this? please let me know