Week 5

Mar 03/27/23

Meeting with Vannary

1. Issue with weighted loss function across multiple gpus #119 (low priority)
2. Runs with 692 videos
   1. method 1: concatenate all seperate test sets DNV, SD1, COV
   2. method 2: combine all: then split 80 (75-25 t&v) 20 test
3. Multi-label defect classification
   1. DNV
   2. SD1
   3. COV
   4. All combined
      1. This is done
4. Run ND vs D
   1. DNV
      1. Both runs are made for both 80 and 486 (486 also includes the previous 80) videos
      2. Runs synced with wandb
      3. Results for test
         1. with fine_tune → done
         2. with fit_flat_cos → not yet
      4. Results compiled?
         1. with fine_tune → done
         2. with fit_flat_cos → not yet
   2. COV
      1. not yet
   3. SD1
      1. not yet
   4. All combined
      1. blah
5. Only defect (no ND) model
   1. DNV
   2. SD1
   3. COV
   4. All combined

Issues with data validation

1. Frames being mislabelled (ND images getting classified as an image containing defect)
   1. point1
   2. point2
   3. point3

fme-to-python

1. break_value assignment remaining for:
   1. mod1: distance based assignment
   2. mod2: distance based assignment
   3. mod3: this is bldg_type based: layout is shared with Vannary

March 28

1. submit n vs defect runs on cedar
2. create the prediction model for top 3 defects using LightGBM
3. run azure OCR on first zipfiles (10 videos) in parallel
4. and send the JSON from the first 10 videos to Deven to train Easy OCR

March 29

1. extract the middle frame for the first 200 out of 1066 WRc videos and group it to different video types base on the distance field

   1. only focus on the distance field
   2. location of the distance
   3. format of the distance

2. what is the best accuracy for binary and for multi-label and put the result in the same sheet.

3. retrain the model on the basic of material and test the the particular materials.

4. use base model and test on the particular materials.

5. use simplified model

6. set aside x videos that has 20% of total number of dataframe. Do it on ND vs Defect model.