Here are the examples of the python api numpy.square taken from open source projects. By voting up you can indicate which examples are most useful and appropriate.
145 Examples
3
View Complete Implementation : deep_conv_classification_alt31.py
Copyright BSD 3-Clause "New" or "Revised" License
Author : SBU-BMI
Copyright BSD 3-Clause "New" or "Revised" License
Author : SBU-BMI
def multi_win_during_val(val_fn, inputs, augs, targets):
for idraw in [100, 110, 120, 130, 140]:
for jdraw in [100, 110, 120, 130, 140]:
inpt_multiwin = data_aug(inputs, mu, sigma, deterministic=True, idraw=idraw, jdraw=jdraw);
err_pat, output_pat = val_fn(inpt_multiwin, augs, targets);
if 'weight' in locals():
dis = ((idraw/100.0-1.0)**2 + (jdraw/100.0-1.0)**2)**0.5;
wei = np.exp(-np.square(dis)/2.0/0.5**2);
weight += wei;
err += err_pat * wei;
output += output_pat * wei;
else:
dis = ((idraw/100.0-1.0)**2 + (jdraw/100.0-1.0)**2)**0.5;
weight = np.exp(-np.square(dis)/2.0/1.0**2);
err = err_pat * weight;
output = output_pat * weight;
return err/weight, output/weight;
3
View Complete Implementation : deep_conv_classification_alt47.py
Copyright BSD 3-Clause "New" or "Revised" License
Author : SBU-BMI
Copyright BSD 3-Clause "New" or "Revised" License
Author : SBU-BMI
def multi_win_during_val(val_fn, inputs, augs, targets):
for idraw in [50, 75, 100, 125, 150]:
for jdraw in [50, 75, 100, 125, 150]:
inpt_multiwin = data_aug(inputs, mu, sigma, deterministic=True, idraw=idraw, jdraw=jdraw);
err_pat, output_pat = val_fn(inpt_multiwin, augs, targets);
if 'weight' in locals():
dis = ((idraw/100.0-1.0)**2 + (jdraw/100.0-1.0)**2)**0.5;
wei = np.exp(-np.square(dis)/2.0/0.5**2);
weight += wei;
err += err_pat * wei;
output += output_pat * wei;
else:
dis = ((idraw/100.0-1.0)**2 + (jdraw/100.0-1.0)**2)**0.5;
weight = np.exp(-np.square(dis)/2.0/1.0**2);
err = err_pat * weight;
output = output_pat * weight;
return err/weight, output/weight;
3
View Complete Implementation : deep_conv_classification_alt48.py
Copyright BSD 3-Clause "New" or "Revised" License
Author : SBU-BMI
Copyright BSD 3-Clause "New" or "Revised" License
Author : SBU-BMI
def multi_win_during_val(val_fn, inputs, augs, targets):
for idraw in [50, 75, 100, 125, 150]:
for jdraw in [50, 75, 100, 125, 150]:
inpt_multiwin = data_aug(inputs, mu, sigma, deterministic=True, idraw=idraw, jdraw=jdraw);
err_pat, output_pat = val_fn(inpt_multiwin, augs, targets);
if 'weight' in locals():
dis = ((idraw/100.0-1.0)**2 + (jdraw/100.0-1.0)**2)**0.5;
wei = np.exp(-np.square(dis)/2.0/0.5**2);
weight += wei;
err += err_pat * wei;
output += output_pat * wei;
else:
dis = ((idraw/100.0-1.0)**2 + (jdraw/100.0-1.0)**2)**0.5;
weight = np.exp(-np.square(dis)/2.0/1.0**2);
err = err_pat * weight;
output = output_pat * weight;
return err/weight, output/weight;
3
View Complete Implementation : deep_conv_classification_alt48maxp_luad10_luad10in20_brca10x1.py
Copyright BSD 3-Clause "New" or "Revised" License
Author : SBU-BMI
Copyright BSD 3-Clause "New" or "Revised" License
Author : SBU-BMI
def multi_win_during_val(val_fn, inputs, augs, targets):
for idraw in [50, 75, 100, 125, 150]:
for jdraw in [50, 75, 100, 125, 150]:
inpt_multiwin = data_aug(inputs, mu, sigma, deterministic=True, idraw=idraw, jdraw=jdraw);
err_pat, output_pat = val_fn(inpt_multiwin, augs, targets);
if 'weight' in locals():
dis = ((idraw/100.0-1.0)**2 + (jdraw/100.0-1.0)**2)**0.5;
wei = np.exp(-np.square(dis)/2.0/0.5**2);
weight += wei;
err += err_pat * wei;
output += output_pat * wei;
else:
dis = ((idraw/100.0-1.0)**2 + (jdraw/100.0-1.0)**2)**0.5;
weight = np.exp(-np.square(dis)/2.0/1.0**2);
err = err_pat * weight;
output = output_pat * weight;
return err/weight, output/weight;
3
View Complete Implementation : deep_conv_classification_alt49.py
Copyright BSD 3-Clause "New" or "Revised" License
Author : SBU-BMI
Copyright BSD 3-Clause "New" or "Revised" License
Author : SBU-BMI
def multi_win_during_val(val_fn, inputs, augs, targets):
for idraw in [50, 75, 100, 125, 150]:
for jdraw in [50, 75, 100, 125, 150]:
inpt_multiwin = data_aug(inputs, mu, sigma, deterministic=True, idraw=idraw, jdraw=jdraw);
err_pat, output_pat = val_fn(inpt_multiwin, augs, targets);
if 'weight' in locals():
dis = ((idraw/100.0-1.0)**2 + (jdraw/100.0-1.0)**2)**0.5;
wei = np.exp(-np.square(dis)/2.0/0.5**2);
weight += wei;
err += err_pat * wei;
output += output_pat * wei;
else:
dis = ((idraw/100.0-1.0)**2 + (jdraw/100.0-1.0)**2)**0.5;
weight = np.exp(-np.square(dis)/2.0/1.0**2);
err = err_pat * weight;
output = output_pat * weight;
return err/weight, output/weight;
3
View Complete Implementation : deep_conv_classification_alt36-sp-cnn.py
Copyright BSD 3-Clause "New" or "Revised" License
Author : SBU-BMI
Copyright BSD 3-Clause "New" or "Revised" License
Author : SBU-BMI
def multi_win_during_val(val_fn, inputs, augs, targets):
for idraw in [50, 75, 100, 125, 150]:
for jdraw in [50, 75, 100, 125, 150]:
inpt_multiwin = data_aug(inputs, mu, sigma, deterministic=True, idraw=idraw, jdraw=jdraw);
err_pat, output_pat = val_fn(inpt_multiwin, augs, targets);
if 'weight' in locals():
dis = ((idraw/100.0-1.0)**2 + (jdraw/100.0-1.0)**2)**0.5;
wei = np.exp(-np.square(dis)/2.0/0.5**2);
weight += wei;
err += err_pat * wei;
output += output_pat * wei;
else:
dis = ((idraw/100.0-1.0)**2 + (jdraw/100.0-1.0)**2)**0.5;
weight = np.exp(-np.square(dis)/2.0/1.0**2);
err = err_pat * weight;
output = output_pat * weight;
return err/weight, output/weight;
3
View Complete Implementation : deep_conv_classification_alt48_luad10in20_brca10.py
Copyright BSD 3-Clause "New" or "Revised" License
Author : SBU-BMI
Copyright BSD 3-Clause "New" or "Revised" License
Author : SBU-BMI
def multi_win_during_val(val_fn, inputs, augs, targets):
for idraw in [50, 75, 100, 125, 150]:
for jdraw in [50, 75, 100, 125, 150]:
inpt_multiwin = data_aug(inputs, mu, sigma, deterministic=True, idraw=idraw, jdraw=jdraw);
err_pat, output_pat = val_fn(inpt_multiwin, augs, targets);
if 'weight' in locals():
dis = ((idraw/100.0-1.0)**2 + (jdraw/100.0-1.0)**2)**0.5;
wei = np.exp(-np.square(dis)/2.0/0.5**2);
weight += wei;
err += err_pat * wei;
output += output_pat * wei;
else:
dis = ((idraw/100.0-1.0)**2 + (jdraw/100.0-1.0)**2)**0.5;
weight = np.exp(-np.square(dis)/2.0/1.0**2);
err = err_pat * weight;
output = output_pat * weight;
return err/weight, output/weight;
3
View Complete Implementation : deep_conv_classification_alt50.py
Copyright BSD 3-Clause "New" or "Revised" License
Author : SBU-BMI
Copyright BSD 3-Clause "New" or "Revised" License
Author : SBU-BMI
def multi_win_during_val(val_fn, inputs, augs, targets):
for idraw in [50, 75, 100, 125, 150]:
for jdraw in [50, 75, 100, 125, 150]:
inpt_multiwin = data_aug(inputs, mu, sigma, deterministic=True, idraw=idraw, jdraw=jdraw);
err_pat, output_pat = val_fn(inpt_multiwin, augs, targets);
if 'weight' in locals():
dis = ((idraw/100.0-1.0)**2 + (jdraw/100.0-1.0)**2)**0.5;
wei = np.exp(-np.square(dis)/2.0/0.5**2);
weight += wei;
err += err_pat * wei;
output += output_pat * wei;
else:
dis = ((idraw/100.0-1.0)**2 + (jdraw/100.0-1.0)**2)**0.5;
weight = np.exp(-np.square(dis)/2.0/1.0**2);
err = err_pat * weight;
output = output_pat * weight;
return err/weight, output/weight;
3
View Complete Implementation : deep_conv_classification_alt48maxp_luad10_luad10in20_brca10x2.py
Copyright BSD 3-Clause "New" or "Revised" License
Author : SBU-BMI
Copyright BSD 3-Clause "New" or "Revised" License
Author : SBU-BMI
def multi_win_during_val(val_fn, inputs, augs, targets):
for idraw in [50, 75, 100, 125, 150]:
for jdraw in [50, 75, 100, 125, 150]:
inpt_multiwin = data_aug(inputs, mu, sigma, deterministic=True, idraw=idraw, jdraw=jdraw);
err_pat, output_pat = val_fn(inpt_multiwin, augs, targets);
if 'weight' in locals():
dis = ((idraw/100.0-1.0)**2 + (jdraw/100.0-1.0)**2)**0.5;
wei = np.exp(-np.square(dis)/2.0/0.5**2);
weight += wei;
err += err_pat * wei;
output += output_pat * wei;
else:
dis = ((idraw/100.0-1.0)**2 + (jdraw/100.0-1.0)**2)**0.5;
weight = np.exp(-np.square(dis)/2.0/1.0**2);
err = err_pat * weight;
output = output_pat * weight;
return err/weight, output/weight;
3
View Complete Implementation : deep_conv_classification_alt51_luad10in20_brca10.py
Copyright BSD 3-Clause "New" or "Revised" License
Author : SBU-BMI
Copyright BSD 3-Clause "New" or "Revised" License
Author : SBU-BMI
def multi_win_during_val(val_fn, inputs, targets):
for idraw in [50, 75, 100, 125, 150]:
for jdraw in [50, 75, 100, 125, 150]:
inpt_multiwin = data_aug(inputs, mu, sigma, deterministic=True, idraw=idraw, jdraw=jdraw);
err_pat, output_pat = val_fn(inpt_multiwin, targets);
if 'weight' in locals():
dis = ((idraw/100.0-1.0)**2 + (jdraw/100.0-1.0)**2)**0.5;
wei = np.exp(-np.square(dis)/2.0/0.5**2);
weight += wei;
err += err_pat * wei;
output += output_pat * wei;
else:
dis = ((idraw/100.0-1.0)**2 + (jdraw/100.0-1.0)**2)**0.5;
weight = np.exp(-np.square(dis)/2.0/1.0**2);
err = err_pat * weight;
output = output_pat * weight;
return err/weight, output/weight;