Skip to main content
stacey
Projects
deep-drive
Reports
Alexnet performs badly at detecting cars
Log in
Sign up
Share
Comment
Star
Share
Comment
Star
Alexnet performs badly at detecting cars
Lukas Biewald
Created on November 30
|
Last edited on November 30
Comment
Section 1
Parameter importance with respect to
car_acc
Parameters
1-10
of 18
Config parameter
Importance
Correlation
encoder.value_alexnet
encoder.value_alexnet
num_train
num_train
num_valid
num_valid
learning_rate
learning_rate
weight_decay
weight_decay
batch_size
batch_size
training_stages
training_stages
bn_weight_decay
bn_weight_decay
epochs
epochs
model_type.value_NAN
model_type.value_NAN
Loading...
iou
iou
Showing first 10 runs
0
5
10
15
Step
0.4
0.5
0.6
0.7
human_acc, iou, car_acc
human_acc, iou, car_acc
5
10
15
20
Time (minutes)
0
0.2
0.4
0.6
0.8
road_acc, car_acc
road_acc, car_acc
0
5
10
15
Step
0.2
0.4
0.6
0.8
Run set
219
Here's what I saw
Add a comment