Open jaentrouble opened 3 years ago
ehr11211_1
lr: lr_step7_2
image_size = (256,384)
epoch 100 steps 500
batch size 32
ehr11211_2
lr: lr_step7_2
changed BN_MOMENTUM to 0.9
epoch 100 steps 500
batch size 32
------------- Abort epoch 74
Does sufficiently well after 50 epochs.
Try smaller model
~mobv3_small~ ehr11211_3
lr: lr_step7_2
Change to MobileNetV3Small
batch size 32
epoch 70 steps 500
~mobv3_small_block~ ehr11211_block
lr: lr_step7_2
Train with mini data to detect a block only
0.pck for train, 1.pck for val (~300 for train, ~180 for val)
Need more data anyway, so see how it can do with this little data
epoch 50 steps 500
mobv3_small_block_2
lr: lr_step7_2
More data
epoch 50 steps 500
No augment other than flipping for now (Will add next time, if it seems essential)
mobv3_small_block_3
lr: lr_step7_2
add shift/rotate augmenting
add parallel generator
batch size 128
epoch 100 steps 500
mobv3_small_head
lr: lr_step7_2
Same as mobv3_small_block_3, but instead of block, track head
To see if block shape was the problem of not detecting well, or the model's size
epoch 100 steps 500
mobv3_small_head_2
lr: lr_step7_2
mix data from before (which also has head)
Add color augmentation
epoch 100, steps 500
mobv3_small_07_head
lr: lr_step7_2
same data config as 8
phi = -2
resolution : (288,224)
backbone: mobv3_small_07
batch size 196
epoch 100, steps 327
Result: Bad. Try different learning rate
Abort at epoch 36 Result: Worse than 10. Try higher learning rate. Maybe too small model?
Error: Dynamic seems to fail. Try again with full integer(with sample)
mobv3_small_07_head_q3q3 (q2 is aborted)
mobv3_small_07_head_q3q4
---------------------- 4 Chamber ----------------------
Result
Train with efficient_hrnet