trainer = unet.Trainer(net,
optimizer="momentum",
opt_kwargs=dict(momentum=0.2))
path = trainer.train(dp,
model_dir,
training_iters=training_iters,
epochs=epochs,
dropout=0.5,
display_step=1000000)
else:
test_files = sorted(glob.glob('../data/data/test/*.h5'))
pred_dir = 'predictions/unet_' + str(features_root) + '/'
rfc.ch_mkdir(pred_dir)
res_file = 'results/unet_' + str(features_root) + '_' + str(threshold)
rfc.ch_mkdir('results')
times = []
pr_list = []
roc_list = []
auc_list = []
clrs = ['b', 'r', 'g', 'k']
trsh = np.linspace(1, 0, 300, endpoint=1)
for fil in test_files:
fname = fil.split('/')[-1]
dp = rfc.DataProvider(a_min=0,
one_hot=1,
thresholds=thresholds,
th_labels=th_labels,
a_min=0, a_max=200)
_,nx,ny,nc = dp(1)[1].shape
print(dp(1)[1].shape)
conv = rfc.ConvolutionalLayers(nx=nx,ny=ny,n_channel=1,n_class=nc,
restore=os.path.exists(model_add),
model_add=model_add,
arch_file_name=arch)
res_file = 'results/threeclass_'+arch+'_'+mode
rfc.ch_mkdir('results')
rfc.ch_mkdir('predictions')
pred_dir = 'predictions/'
times = []
cnf_matrix = []
for fil in test_files:
fname = fil.split('/')[-1]
dp = rfc.DataProvider(files=[fil],label_name='RFI',
one_hot=1,
thresholds=thresholds,
th_labels=th_labels,
a_min=0, a_max=200)
data,mask = dp(1)
conv.train(data_provider=dp,
training_epochs=10000000,
n_s=n_rounds,
learning_rate=learning_rate,
dropout=0.7,
time_limit=time_limit // n_rounds,
verbose=1)
learning_rate = learning_rate / 4.
else:
import pickle
# pred_dir = 'predictions/threeclass_'+arch+'_'+mode+'/'
# rfc.ch_mkdir(pred_dir)
res_file = 'results/threeclass_' + arch + '_' + mode
rfc.ch_mkdir('results')
# weights = conv.get_filters()
# with open(res_file+'_filters', 'w') as filehandler:
# pickle.dump(weights, filehandler)
# np.save(res_file+'_filters',weights)
test_files = sorted(
glob.glob('../../../data/hide_sims_test/calib_1month/*.fits'))
times = []
pr_list = []
roc_list = []
auc_list = []
cnf_matrix = []
import matplotlib as mpl
mpl.use('agg')
import os
import glob
import numpy as np
import pylab as plt
from matplotlib.colors import LogNorm
import rficnn as rfc
dss = ['training', 'validation', 'test']
rfc.ch_mkdir('plots')
for ds in dss:
test_files = sorted(glob.glob('../../../data/kat7/dataset/' + ds +
'/*.h5'))
for fil in test_files:
fname = fil.split('/')[-1]
dp = rfc.DataProvider(a_min=0,
a_max=100,
files=[fil],
label_name='mask')
data, mask = dp(1)
mask = mask[0, :, :, 0]
fig, (ax1, ax2) = plt.subplots(2, 1, figsize=(12, 8))
