AntoineH/smart_augmentation
1
0
Fork 0
mirror of https://github.com/AntoineHX/smart_augmentation.git synced 2025-05-04 04:00:46 +02:00
Code Issues Projects Releases Packages Wiki Activity

Confmat / F1 + Minor fix

Browse source
This commit is contained in:
Harle, Antoine (Contracteur) 2020-01-31 16:43:10 -05:00
parent 250ce2c3cf
commit 3ccacd0366
5 changed files with 120 additions and 32 deletions
Download patch file Download diff file Expand all files Collapse all files

27
higher/smart_aug/test_dataug.py
View file

@ -1,7 +1,7 @@
""" Script to run experiment on smart augmentation.
"""
import sys
from LeNet import *
from dataug import *
#from utils import *
@ -79,7 +79,7 @@ if __name__ == "__main__":
}
#Parameters
n_inner_iter = 1
epochs = 150
epochs = 2
dataug_epoch_start=0
optim_param={
'Meta':{
@ -94,18 +94,21 @@ if __name__ == "__main__":
}
#Models
model = LeNet(3,10)
#model = LeNet(3,10)
#model = ResNet(num_classes=10)
#import torchvision.models as models
import torchvision.models as models
#model=models.resnet18()
model_name = 'resnet18' #'wide_resnet50_2' #'resnet18' #str(model)
model = getattr(models.resnet, model_name)(pretrained=False)
#### Classic ####
if 'classic' in tasks:
t0 = time.process_time()
model = model.to(device)
print("{} on {} for {} epochs".format(str(model), device_name, epochs))
log= train_classic(model=model, opt_param=optim_param, epochs=epochs, print_freq=20)
print("{} on {} for {} epochs".format(model_name, device_name, epochs))
log= train_classic(model=model, opt_param=optim_param, epochs=epochs, print_freq=5)
#log= train_classic_higher(model=model, epochs=epochs)
exec_time=time.process_time() - t0
@ -114,12 +117,12 @@ if __name__ == "__main__":
times = [x["time"] for x in log]
out = {"Accuracy": max([x["acc"] for x in log]), "Time": (np.mean(times),np.std(times), exec_time), 'Optimizer': optim_param['Inner'], "Device": device_name, "Log": log}
print(str(model),": acc", out["Accuracy"], "in:", out["Time"][0], "+/-", out["Time"][1])
filename = "{}-{} epochs".format(str(model),epochs)
filename = "{}-{} epochs".format(model_name,epochs)
with open("../res/log/%s.json" % filename, "w+") as f:
json.dump(out, f, indent=True)
print('Log :\"',f.name, '\" saved !')
plot_res(log, fig_name="../res/"+filename)
#plot_res(log, fig_name="../res/"+filename)
print('Execution Time : %.00f '%(exec_time))
print('-'*9)
@ -129,8 +132,8 @@ if __name__ == "__main__":
t0 = time.process_time()
tf_dict = {k: TF.TF_dict[k] for k in tf_names}
model = Higher_model(model) #run_dist_dataugV3
aug_model = Augmented_model(Data_augV5(TF_dict=tf_dict, N_TF=3, mix_dist=0.8, fixed_prob=False, fixed_mag=False, shared_mag=False), model).to(device)
model = Higher_model(model, model_name) #run_dist_dataugV3
aug_model = Augmented_model(Data_augV5(TF_dict=tf_dict, N_TF=2, mix_dist=0.8, fixed_prob=False, fixed_mag=False, shared_mag=False), model).to(device)
#aug_model = Augmented_model(RandAug(TF_dict=tf_dict, N_TF=2), model).to(device)
print("{} on {} for {} epochs - {} inner_it".format(str(aug_model), device_name, epochs, n_inner_iter))
@ -139,7 +142,7 @@ if __name__ == "__main__":
inner_it=n_inner_iter,
dataug_epoch_start=dataug_epoch_start,
opt_param=optim_param,
print_freq=20,
print_freq=1,
unsup_loss=1,
hp_opt=False,
save_sample_freq=None)
@ -157,10 +160,12 @@ if __name__ == "__main__":
print('Log :\"',f.name, '\" saved !')
except:
print("Failed to save logs :",f.name)
print(sys.exc_info()[0])
try:
plot_resV2(log, fig_name="../res/"+filename, param_names=aug_model.TF_names())
except:
print("Failed to plot res")
print(sys.exc_info()[0])
print('Execution Time : %.00f '%(exec_time))
print('-'*9)