def main():
"""Main Function."""
# dataloader parameters
gpu = torch.cuda.is_available()
train_path = 'data/train_data.txt'
valid_path = 'data/valid_data.txt'
batch_size = 20
sequence_len = 50
num_workers = 2
# training parameters
max_epochs = 200
learning_rate = 1e-4
criterion = nn.CrossEntropyLoss()
# get dataloaders
dataloaders, dataset_sizes = get_loaders(train_path, valid_path,
batch_size, sequence_len,
num_workers, gpu)
# create network and optimizier
net = SingleFrame('VGGNet19')
print(net)
optimizer = torch.optim.Adam(net.parameters(), learning_rate)
# train the network
net, val_acc, losses, accuracies = train_network(net, dataloaders,
dataset_sizes, batch_size,
sequence_len, criterion,
optimizer, max_epochs,
gpu)
print('Best Validation Acc:', val_acc)
# plot
plot_data(losses, accuracies, 'outputs/online/SingleFramePlots.png')
# save network
torch.save(net.state_dict(), 'outputs/online/SingleFrameParams.pkl')
def evaluate((data, dq, shifts, psf_model, parms, core)):
"""
Compute the scaled squared error and regularization under the current
model.
"""
if core:
patch_shape = parms.core_shape
else:
patch_shape = parms.patch_shape
min_pixels = np.ceil(parms.min_frac * patch_shape[0] * patch_shape[1])
psfs = render_psfs(psf_model, shifts, patch_shape, parms.psf_grid, parms.k)
if parms.return_parms:
if parms.background == 'constant':
fit_parms = np.zeros((data.shape[0], 2))
else:
fit_parms = np.zeros((data.shape[0], 4))
masks = np.zeros_like(data, dtype=np.bool)
nll = np.zeros_like(data)
for i in range(data.shape[0]):
fitparms, bkg, ind = fit_single_patch((data[i], psfs[i],
dq[i], parms))
model = fitparms[0] * psfs[i] + bkg
scaled = fitparms[0] * psfs[i]
# chi-squared like term
if (model[ind].size >= min_pixels):
nll[i, ind] = eval_nll(data[i][ind], model[ind], parms)
else:
nll[i] = parms.max_nll
if parms.plot_data:
# get pre-clip nll
ind = parms.flags.ravel() != 1
old_nll = np.zeros(patch_shape[0] * patch_shape[1])
old_nll[ind] = eval_nll(data[i][ind], parms.old_model[ind], parms)
# plot the data
plot_data(i, data[i], model, bkg, nll[i], old_nll, parms)
if parms.return_parms:
fit_parms[i] = fitparms
masks[i] = ind
if parms.return_parms:
return nll, fit_parms, masks
else:
return nll
def main():
"""Main Function."""
# dataloader parameters
gpu = torch.cuda.is_available()
train_path = 'data/train_data.txt'
valid_path = 'data/valid_data.txt'
batch_size = 2
sequence_len = 50
window_size = 5
flow = False
num_workers = 2
# network parameters
model = 'VGGNet19'
rnn_hidden = 512
rnn_layers = 1
# training parameters
max_epochs = 1
learning_rate = 1e-4
criterion = nn.CrossEntropyLoss()
# get loaders
dataloaders, dataset_sizes = get_loaders(train_path, valid_path,
batch_size, sequence_len,
window_size, flow, num_workers,
gpu)
# create network and optimizer
net = SingleStream(model, rnn_hidden, rnn_layers, pretrained=True)
print(net)
optimizer = torch.optim.Adam(net.parameters(), learning_rate)
# train the network
net, val_acc, losses, accuracies = train_network(net, dataloaders,
dataset_sizes, batch_size,
sequence_len, window_size,
criterion, optimizer,
max_epochs, gpu)
# plot
if flow:
s_plots = 'outputs/online/SingleStreamFlowPlots.png'
s_params = 'outputs/online/SingleStreamFlowParams.pkl'
else:
s_plots = 'outputs/online/SingleStreamAppPlots.png'
s_params = 'outputs/online/SingleStreamAppParams.pkl'
# plot
plot_data(losses, accuracies, s_plots)
# save network
torch.save(net.state_dict(), s_params)
def look_at_and_pre_process_data(data, rawdata, variables):
# Now plot the input data.
show_data = raw_input("Show the raw-data? (1 = YES): ")
if show_data == '1':
pl.plot_data(data, variables)
# Preprocess the data (mean-centering, normalization).
text_1 = "Pre-process the data (ENTER = normalization AND mean centering, "
text_2 = "1 = JUST mean centering, 0 = None): "
these_processes = raw_input(text_1 + text_2)
data, rawdata = dp.preprocess_data(these_processes, data, rawdata)
# "Enhance" certain variables to put all their influence into one component.
text = "Enhance variables? As integers: Variable_1, Variable_2, ... ; ENTER = none): "
enhance_these = raw_input(text)
data, rawdata = dp.boost_variables(enhance_these, data, rawdata)
def main():
"""Main Function."""
# dataloader parameters
gpu = torch.cuda.is_available()
train_path = 'data/train_data.txt'
valid_path = 'data/valid_data.txt'
batch_size = 2
sequence_len = 10
num_workers = 2
# network parameters
spat_model = 'VGGNet11'
temp_model = 'VGGNet11'
rnn_hidden = 32
rnn_layers = 1
# training parameters
max_epochs = 2
learning_rate = 1e-4
window_size = 5
criterion = nn.CrossEntropyLoss()
# get loaders
dataloaders, dataset_sizes = get_loaders(train_path, valid_path,
batch_size, sequence_len, flow,
num_workers, gpu)
# create network and optimizer
net = TwoStreamFusion(spat_model,
temp_model,
rnn_hidden,
rnn_layers,
pretrained=False)
print(net)
optimizer = torch.optim.Adam(net.parameters(), learning_rate)
# train the network
net, val_acc, losses, accuracies = train_network(
net, dataloaders, dataset_sizes, batch_size, sequence_len - 1,
window_size, criterion, optimizer, max_epochs, gpu)
# plot
plot_data(losss, accuracies, 'outputs/online/TwoStreamPlots.png')
# save network
torch.save(net.state_dict(), 'outputs/online/TwoStreamParams.pkl')
def main():
"""Main Function."""
# dataloaders parameters
gpu = torch.cuda.is_available()
train_path = 'data/train_data.txt'
valid_path = 'data/valid_data.txt'
test_path = 'data/test_data.txt'
batch_size = 32
num_workers = 2
# network parameters
model = 'VGGNet19'
rnn_hidden = 512
rnn_layers = 2
# training parameters
max_epochs = 100
learning_rate = 1e-4
criterion = nn.CrossEntropyLoss()
# create dataloaders
dataloaders, dataset_sizes = get_loaders(train_path,
valid_path,
batch_size,
num_workers,
gpu=True)
print('Dataset Sizes:')
print(dataset_sizes)
# create network object and optimizer
net = SingleStream(model, rnn_hidden, rnn_layers, pretrained=True)
print(net)
optimizer = torch.optim.Adam(net.parameters(), learning_rate)
# train the network
net, val_acc, losses, accuracies = train_network(net, dataloaders,
dataset_sizes, batch_size,
criterion, optimizer,
max_epochs, gpu)
# plot
plot_data(losses, accuracies, 'outputs/offline/SingleStreamPlots.png')
# save network
torch.save(net.state_dict(), 'outputs/offline/SingleStreamParams.pkl')
str("files/" +
str(SET_OF_PARAMETERS).replace('parameters_', '') +
'_histos.dat'))
save_histo(
[e.time for t, e in histories_for_scan[key].items()],
[e.TOT for t, e in histories_for_scan[key].items()],
h_name, "files/" +
str(SET_OF_PARAMETERS).replace('parameters_', '') +
'_histos.dat')
if parameters_store["simulation_parameters"]["DISPLAY_DATA"] != "FALSE":
from utils import read_data, save_histo
dataset = read_data(
parameters_store["simulation_parameters"]["DISPLAY_DATA"])
from plotting import plot_data, plot_data_vs_model
plot_data(dataset)
plot_data_vs_model(dataset, history, parameters_store,
SET_OF_PARAMETERS)
if parameters_store["simulation_parameters"][
"SAVE_HISTOGRAMS"] != "FALSE":
print('..storing h_data ' +
str("files/" +
str(SET_OF_PARAMETERS).replace('parameters_', '') +
'_histos.dat'))
save_histo(
dataset["t"], dataset["tot"], 'h_data',
"files/" + str(SET_OF_PARAMETERS).replace('parameters_', '') +
'_histos.dat')
if parameters_store["simulation_parameters"]["IMPROVED_MODEL"] != "FALSE":
NUM_WORDS_AFTER_VERB, ACTIVATIONS, PRINT_PLOTTING_INFO)
modified_correct_plotting_dict, modified_wrong_plotting_dict = diagnostic_experiment.run_diagnostic_experiment(
training_filepath_2, modified_testing_filepaths,
MODIFIED_RESULTS_PATHS, None, MODE, CONTEXT_SIZE_LIST,
NUM_WORDS_BEFORE_SUBJECT, NUM_WORDS_AFTER_VERB, ACTIVATIONS,
PRINT_PLOTTING_INFO)
if MODIFICATION:
plotting.plot_modified_data(correct_plotting_dict,
wrong_plotting_dict,
modified_correct_plotting_dict,
modified_wrong_plotting_dict,
plot_savefile, MODE)
else:
plotting.plot_data(correct_plotting_dict, wrong_plotting_dict,
plot_savefile, MODE)
elif LABELS_TYPE == 'training_normal':
correct_plotting_dict, wrong_plotting_dict = diagnostic_experiment.run_diagnostic_experiment_timestep_training(
training_filepath_2, testing_filepaths, RESULTS_PATHS, None,
MODE, CONTEXT_SIZE_LIST, NUM_WORDS_BEFORE_SUBJECT,
NUM_WORDS_AFTER_VERB, ACTIVATIONS, PRINT_PLOTTING_INFO)
modified_correct_plotting_dict, modified_wrong_plotting_dict = diagnostic_experiment.run_diagnostic_experiment_timestep_training(
training_filepath_2, modified_testing_filepaths,
MODIFIED_RESULTS_PATHS, None, MODE, CONTEXT_SIZE_LIST,
NUM_WORDS_BEFORE_SUBJECT, NUM_WORDS_AFTER_VERB, ACTIVATIONS,
PRINT_PLOTTING_INFO)
if MODIFICATION:
plotting.plot_modified_data(correct_plotting_dict,
modified_correct_plotting_dict, modified_wrong_plotting_dict = diagnostic_experiment.run_diagnostic_experiment(training_filepath_2,
modified_testing_filepaths,
MODIFIED_RESULTS_PATHS,
None,
MODE,
CONTEXT_SIZE_LIST,
NUM_WORDS_BEFORE_SUBJECT,
NUM_WORDS_AFTER_VERB,
ACTIVATIONS,
PRINT_PLOTTING_INFO)
if MODIFICATION:
plotting.plot_modified_data(correct_plotting_dict, wrong_plotting_dict, modified_correct_plotting_dict, modified_wrong_plotting_dict, plot_savefile, MODE)
else:
plotting.plot_data(correct_plotting_dict, wrong_plotting_dict, plot_savefile, MODE)
elif LABELS_TYPE == 'training_normal':
correct_plotting_dict, wrong_plotting_dict = diagnostic_experiment.run_diagnostic_experiment_timestep_training(training_filepath_2,
testing_filepaths,
RESULTS_PATHS,
None,
MODE,
CONTEXT_SIZE_LIST,
NUM_WORDS_BEFORE_SUBJECT,
NUM_WORDS_AFTER_VERB,
ACTIVATIONS,
PRINT_PLOTTING_INFO)
modified_correct_plotting_dict, modified_wrong_plotting_dict = diagnostic_experiment.run_diagnostic_experiment_timestep_training(training_filepath_2,
modified_testing_filepaths,
ct0_samples = samples['ct0']
ct1_samples = samples['ct1']
ct2_samples = samples['ct2']
ct3_samples = samples['ct3']
ct4_samples = samples['ct4']
ct5_samples = samples['ct5']
v_samples = samples['voltage']
# Save samples to disk
with open('data/samples/last-debug.pkl', 'wb') as f:
pickle.dump(samples, f)
if not title:
title = input("Enter the title for this chart: ")
plot_data(samples, title)
ip = get_ip()
if ip:
logger.info(
f"Chart created! Visit http://{ip}/{title}.html to view the chart. Or, simply visit http://{ip} to view all the charts created using 'debug' and/or 'phase' mode."
)
else:
logger.info(
"Chart created! I could not determine the IP address of this machine. Visit your device's IP address in a webrowser to view the list of charts you've created using 'debug' and/or 'phase' mode."
)
if MODE.lower() == 'phase':
# This mode is intended to be used for correcting the phase error in your CT sensors. Instead of reading the CT sensors, it will open the 'last-debug.pkl' file and read the contents, which
# contain the samples from the last time the program was ran in "debug" mode. This is to save electricity so you don't need to keep your resistive load device running while you calibrate.
# The function then continues to build 5 different variations of the raw AC voltage wave based on the ct#_phasecal variable.
# Finally, a single chart is constructed that shows all of the raw CT data points, the "as measured" voltage wave, and the phase corrected voltage wave. The chart is written to an HTML file
num_correct_clean_d2[s] = num_correct_clean_d2[s] + 1
if class_adv_defended == yB:
num_correct_rob_a2d2[s] = num_correct_rob_a2d2[s] + 1
num_imgs += 1
print(num_imgs)
from plotting import plot_data
plot_data(sigmas=sigmas,
num_imgs=num_imgs,
num_adv_success_a1d0=num_adv_success_a1d0,
num_correct_clean_d0=num_correct_clean_d0,
num_correct_rob_a1d0=num_correct_rob_a1d0,
num_adv_success_a1d1=num_adv_success_a1d1,
num_correct_clean_d1=num_correct_clean_d1,
num_correct_rob_a1d1=num_correct_rob_a1d1,
num_adv_success_a2d1=num_adv_success_a2d1,
num_correct_rob_a2d1=num_correct_rob_a2d1,
num_adv_success_a2d2=num_adv_success_a2d2,
num_correct_clean_d2=num_correct_clean_d2,
num_correct_rob_a2d2=num_correct_rob_a2d2)
#
# print(sigmas)
# print(num_correct_clean)
# print(num_correct_rob)
# print(num_correct_rob2)
# print(num_adv_success)
# print(num_better_adv_success)
import pdb
# Z = X**q # Z = data.add_bias(Z) # W,stats = pocket_perceptron.perceptron(Z,y) # print(W) # plotting.plot_mesh(W,X,q=q) # plotting.plot_data(X,y=y,title=title) # plotting.plot_transform(W,q=q) # plotting.show() # ======================================= # graphing testing X,f = data.qth_order_data(lower=-8000,upper=10,q=5,n=100000) z_ = data.zoom_limits(X) print(z_) X = data.increase_resolution(f,z_) plotting.plot_data(X) plotting.set_limits(z_) plotting.show() # ======================================== # linear fit testing # X,f = data.qth_order_data(q=q,n=50,noise=noise) # plotting.plot_data(X) # # returns function # p = linear_regression.linear_regression(X,q=q_fit) # plotting.polynomial(p,X) # print(p.error()) # z_ = data.zoom_limits(X) # print(z_)
def compute_square_eigenvalues(write_out=False):
"""Compute Laplace Dirichlet eigenvalues of the square"""
a = 2
N = 25
num_pts = 2*N
k = np.arange(1,N).reshape(N-1,1)
# expand about origin
x1 = np.ones(num_pts)
y1 = np.linspace(0,1,num_pts)
x2 = np.linspace(0,1,num_pts)
y2 = np.ones(num_pts)
xint = np.random.random(2*num_pts)
yint = np.random.random(2*num_pts)
x = np.concatenate( (x1, x2, xint) )
y = np.concatenate( (y1, y2, yint) )
plt.scatter(x,y)
plt.axes().set_aspect('equal')
plt.show()
r = np.sqrt(x**2 + y**2)
t = np.arctan2(y,x)
lams = np.arange(0.5, 100, 0.5)
S = []
Alist = []
for lam in lams:
A = evaluate_basis_func_bessel(a, lam, r, t, k)
Alist.append(A)
S.append(find_sing_val(A,4*N))#2*num_pts))
if write_out:
with open('shape.dat', 'w+') as f:
for n in range(4*num_pts):
f.write( str(r[n]*np.cos(t[n]))+' '+str(r[n]*np.sin(t[n])) + '\n')
with open('out.dat', 'w+') as f:
for n in range(len(lams)):
f.write( str(lams[n]) + ' ' + str(S[n]) + '\n')
mins = []
for i in range(len(lams))[1:-1]:
if S[i-1] > S[i] and S[i+1] > S[i]:
mins.append(lams[i])
print mins
eigs = []
for m in range(1,5):
for n in range(1,5):
eigs.append( np.pi**2*(m**2 + n**2) )
print sorted(eigs)
return lams, S, Alist
if write_out:
plot_data(lams, [S], ['minimum singular value'], 'minimum singular value',
'frequency', 'sing value', 'sing_vals.html')
def fit_patches(data, dq, shifts, psf_model, parms, old_fit_parms=None):
"""
Fit the patches and return model components and nll.
"""
# initialize
nll = np.zeros_like(data)
masks = np.zeros_like(data, dtype=np.bool)
if parms.background == None:
fit_parms = np.zeros(data.shape[0])
elif parms.background == 'constant':
fit_parms = np.zeros((data.shape[0], 2))
else:
assert 0, 'no linear bkgs, need to implement uncertainties'
fit_parms = np.zeros((data.shape[0], 4))
fit_vars = np.zeros_like(fit_parms)
psfs = render_psfs(psf_model, shifts, parms.patch_shape, parms.psf_grid,
parms.k)
for i in range(data.shape[0]):
dlt_nll = np.inf
if old_fit_parms == None:
fp, fv, bkg, ind = fit_single_patch(data[i], psfs[i], dq[i], parms)
else:
bkg = make_background(data[i], old_fit_parms[i], parms.background)
model = old_fit_parms[i][0] * psfs[i] + bkg
nm = parms.floor + parms.gain * np.abs(model)
fp, fv, bkg, ind = fit_single_patch(data[i], psfs[i], dq[i], parms,
var=nm)
model = fp[0] * psfs[i] + bkg
nm = parms.floor + parms.gain * np.abs(model)
cur_nll = np.sum(patch_nll(data[i][ind], model[ind], parms))
cur_fp = fp
cur_fv = fv
while dlt_nll > parms.nll_tol:
fp, fv, bkg, idx = fit_single_patch(data[i], psfs[i], dq[i], parms,
var=nm)
model = fp[0] * psfs[i] + bkg
nm = parms.floor + parms.gain * np.abs(model)
new_nll = np.sum(patch_nll(data[i][idx], model[idx], parms))
dlt_nll = cur_nll - new_nll
if dlt_nll > 0:
ind = idx
cur_fp = fp
cur_fv = fv
cur_nll = new_nll
assert cur_nll < parms.max_nll
nll[i, ind] = cur_nll
masks[i] = ind
fit_parms[i] = cur_fp
fit_vars[i] = cur_fv
if parms.plot_data:
# get pre-clip nll
if parms.clip_parms == None:
parms.old_model = model
parms.old_bkg = bkg
flags = dq[i].reshape(parms.patch_shape)
flags[flags > 1] = 1
parms.flags = flags
else:
ind = parms.flags.ravel() != 1
old_nll = np.zeros(data.shape[1])
old_nll[ind] = patch_nll(data[i][ind], parms.old_model[ind], parms)
# plot the data
t = time.time()
plot_data(i, data[i], model, bkg, nll[i], old_nll, parms)
return fit_parms, fit_vars, nll, masks
def compute_square_eigenvalues(write_out=False):
"""Compute Laplace Dirichlet eigenvalues of the square"""
a = 2
N = 25
num_pts = 2 * N
k = np.arange(1, N).reshape(N - 1, 1)
# expand about origin
x1 = np.ones(num_pts)
y1 = np.linspace(0, 1, num_pts)
x2 = np.linspace(0, 1, num_pts)
y2 = np.ones(num_pts)
xint = np.random.random(2 * num_pts)
yint = np.random.random(2 * num_pts)
x = np.concatenate((x1, x2, xint))
y = np.concatenate((y1, y2, yint))
plt.scatter(x, y)
plt.axes().set_aspect('equal')
plt.show()
r = np.sqrt(x**2 + y**2)
t = np.arctan2(y, x)
lams = np.arange(0.5, 100, 0.5)
S = []
Alist = []
for lam in lams:
A = evaluate_basis_func_bessel(a, lam, r, t, k)
Alist.append(A)
S.append(find_sing_val(A, 4 * N)) #2*num_pts))
if write_out:
with open('shape.dat', 'w+') as f:
for n in range(4 * num_pts):
f.write(
str(r[n] * np.cos(t[n])) + ' ' + str(r[n] * np.sin(t[n])) +
'\n')
with open('out.dat', 'w+') as f:
for n in range(len(lams)):
f.write(str(lams[n]) + ' ' + str(S[n]) + '\n')
mins = []
for i in range(len(lams))[1:-1]:
if S[i - 1] > S[i] and S[i + 1] > S[i]:
mins.append(lams[i])
print mins
eigs = []
for m in range(1, 5):
for n in range(1, 5):
eigs.append(np.pi**2 * (m**2 + n**2))
print sorted(eigs)
return lams, S, Alist
if write_out:
plot_data(lams, [S], ['minimum singular value'],
'minimum singular value', 'frequency', 'sing value',
'sing_vals.html')
plt.plot(N,i_iterations,label='iterative')
plt.xlabel("Number of data points")
plt.ylabel("Number of iterations")
plt.ylim(-.0001,min(np.max(v_iterations),np.max(i_iterations)))
plt.legend()
plt.title("Comparison of Vectorized versus Iterative number of iterations")
plt.show()
if __name__ == '__main__':
d=2
n=100
f = np.random.rand(d+1)
f[1]*=-1
#vector_vs_iterative(f,n,d)
X,y = data.data(f,n,d,classify)
W,stats = perceptron(X,y)
print("W:",W)
plotting.plot_mesh(W,X)
plotting.plot_implicit(W)
plotting.plot_data(X,y=y)
a,b,c=W
plt.title("Ordinary Perceptron\nSlope: {:.2f} | Intercept: {:.2f}".format(-a/b,-c/b))
plt.show()
def baseline(args):
args = parse_arguments(args)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
file_helper = FileHelper()
train_helper = TrainHelper(device)
train_helper.seed_torch(seed=args.seed)
model_name = train_helper.get_filename_from_baseline_params(args)
run_folder = file_helper.get_run_folder(args.folder, model_name)
metrics_helper = MetricsHelper(run_folder, args.seed)
# get sender and receiver models and save them
sender, receiver, diagnostic_receiver = get_sender_receiver(device, args)
sender_file = file_helper.get_sender_path(run_folder)
receiver_file = file_helper.get_receiver_path(run_folder)
# torch.save(sender, sender_file)
if receiver:
torch.save(receiver, receiver_file)
model = get_trainer(
sender,
device,
args.dataset_type,
receiver=receiver,
diagnostic_receiver=diagnostic_receiver,
vqvae=args.vqvae,
rl=args.rl,
entropy_coefficient=args.entropy_coefficient,
myopic=args.myopic,
myopic_coefficient=args.myopic_coefficient,
)
model_path = file_helper.create_unique_model_path(model_name)
best_accuracy = -1.0
epoch = 0
iteration = 0
if args.resume_training or args.test_mode:
epoch, iteration, best_accuracy = load_model_state(model, model_path)
print(
f"Loaded model. Resuming from - epoch: {epoch} | iteration: {iteration} | best accuracy: {best_accuracy}"
)
if not os.path.exists(file_helper.model_checkpoint_path):
print("No checkpoint exists. Saving model...\r")
torch.save(model.visual_module, file_helper.model_checkpoint_path)
print("No checkpoint exists. Saving model...Done")
train_data, valid_data, test_data, valid_meta_data, _ = get_training_data(
device=device,
batch_size=args.batch_size,
k=args.k,
debugging=args.debugging,
dataset_type=args.dataset_type,
)
train_meta_data, valid_meta_data, test_meta_data = get_meta_data()
# dump arguments
pickle.dump(args, open(f"{run_folder}/experiment_params.p", "wb"))
pytorch_total_params = sum(p.numel() for p in model.parameters())
if not args.disable_print:
# Print info
print("----------------------------------------")
print(
"Model name: {} \n|V|: {}\nL: {}".format(
model_name, args.vocab_size, args.max_length
)
)
print(sender)
if receiver:
print(receiver)
if diagnostic_receiver:
print(diagnostic_receiver)
print("Total number of parameters: {}".format(pytorch_total_params))
model.to(device)
optimizer = torch.optim.Adam(model.parameters(), lr=args.lr)
# Train
current_patience = args.patience
best_accuracy = -1.0
converged = False
start_time = time.time()
if args.test_mode:
test_loss_meter, test_acc_meter, _ = train_helper.evaluate(
model, test_data, test_meta_data, device, args.rl
)
average_test_accuracy = test_acc_meter.avg
average_test_loss = test_loss_meter.avg
print(
f"TEST results: loss: {average_test_loss} | accuracy: {average_test_accuracy}"
)
return
iterations = []
losses = []
hinge_losses = []
rl_losses = []
entropies = []
accuracies = []
while iteration < args.iterations:
for train_batch in train_data:
print(f"{iteration}/{args.iterations} \r", end="")
### !!! This is the complete training procedure. Rest is only logging!
_, _ = train_helper.train_one_batch(
model, train_batch, optimizer, train_meta_data, device
)
if iteration % args.log_interval == 0:
if not args.rl:
valid_loss_meter, valid_acc_meter, _, = train_helper.evaluate(
model, valid_data, valid_meta_data, device, args.rl
)
else:
valid_loss_meter, hinge_loss_meter, rl_loss_meter, entropy_meter, valid_acc_meter, _ = train_helper.evaluate(
model, valid_data, valid_meta_data, device, args.rl
)
new_best = False
average_valid_accuracy = valid_acc_meter.avg
if (
average_valid_accuracy < best_accuracy
): # No new best found. May lead to early stopping
current_patience -= 1
if current_patience <= 0:
print("Model has converged. Stopping training...")
converged = True
break
else: # new best found. Is saved.
new_best = True
best_accuracy = average_valid_accuracy
current_patience = args.patience
save_model_state(model, model_path, epoch, iteration, best_accuracy)
# Skip for now <--- What does this comment mean? printing is not disabled, so this will be shown, right?
if not args.disable_print:
if not args.rl:
print(
"{}/{} Iterations: val loss: {}, val accuracy: {}".format(
iteration,
args.iterations,
valid_loss_meter.avg,
valid_acc_meter.avg,
)
)
else:
print(
"{}/{} Iterations: val loss: {}, val hinge loss: {}, val rl loss: {}, val entropy: {}, val accuracy: {}".format(
iteration,
args.iterations,
valid_loss_meter.avg,
hinge_loss_meter.avg,
rl_loss_meter.avg,
entropy_meter.avg,
valid_acc_meter.avg,
)
)
iterations.append(iteration)
losses.append(valid_loss_meter.avg)
if args.rl:
hinge_losses.append(hinge_loss_meter.avg)
rl_losses.append(rl_loss_meter.avg)
entropies.append(entropy_meter.avg)
accuracies.append(valid_acc_meter.avg)
iteration += 1
if iteration >= args.iterations:
break
epoch += 1
if converged:
break
# prepare writing of data
dir_path = os.path.dirname(os.path.realpath(__file__))
dir_path = dir_path.replace("/baseline", "")
timestamp = str(datetime.datetime.now())
filename = "output_data/vqvae_{}_rl_{}_dc_{}_gs_{}_dln_{}_dld_{}_beta_{}_entropy_coefficient_{}_myopic_{}_mc_{}_seed_{}_{}.csv".format(
args.vqvae,
args.rl,
args.discrete_communication,
args.gumbel_softmax,
args.discrete_latent_number,
args.discrete_latent_dimension,
args.beta,
args.entropy_coefficient,
args.myopic,
args.myopic_coefficient,
args.seed,
timestamp,
)
full_filename = os.path.join(dir_path, filename)
# write data
d = [iterations, losses, hinge_losses, rl_losses, entropies, accuracies]
export_data = zip_longest(*d, fillvalue="")
with open(full_filename, "w", encoding="ISO-8859-1", newline="") as myfile:
wr = csv.writer(myfile)
wr.writerow(
("iteration", "loss", "hinge loss", "rl loss", "entropy", "accuracy")
)
wr.writerows(export_data)
myfile.close()
# plotting
print(filename)
plot_data(filename, args)
return run_folder
ct2_samples = samples['ct2']
ct3_samples = samples['ct3']
ct4_samples = samples['ct4']
ct5_samples = samples['ct5']
v_samples = samples['voltage']
# Save samples to disk
with open('data/samples/last-debug.pkl', 'wb') as f:
pickle.dump(samples, f)
if not title:
title = input("Enter the title for this chart: ")
title = title.replace(" ", "_")
logger.debug("Building plot.")
plot_data(samples, title)
ip = get_ip()
if ip:
logger.info(
f"Chart created! Visit http://{ip}/{title}.html to view the chart. Or, simply visit http://{ip} to view all the charts created using 'debug' and/or 'phase' mode."
)
else:
logger.info(
"Chart created! I could not determine the IP address of this machine. Visit your device's IP address in a webrowser to view the list of charts you've created using 'debug' and/or 'phase' mode."
)
if MODE.lower() == 'phase':
# This mode is intended to be used for correcting the phase error in your CT sensors. Please ensure that you have a purely resistive load running through your CT sensors - that means no electric fans and no digital circuitry!
PF_ROUNDING_DIGITS = 3 # This variable controls how many decimal places the PF will be rounded
def calculate_metric_terms(cand=None,
cluster_function=None,
plot=False,
debug=False,
**kwargs):
"""
Calculate metric values
:param cand: Candidates from an observation with the four features, snr, and base label (RFI or FRB).
:param cluster_function: Function to use for clustering
:param plot: To plot the results
:param debug: More logging for debugging
:param kwargs: Arguments for the clustering function
:return:
Number of candidates
FRB found: True if FRB candidates were recovered
homogenity_frbs: homogenity of the FRBs
completenes_frbs: completenes of the FRBs
v_measure: V measure value
"""
if isinstance(cand, dict):
d = cand['cands']
l = cand['labels']
s = cand['snrs']
data = d
else:
f = np.load(cand)
if debug:
print(cand)
d = f['cands']
l = f['labels']
s = f['snrs']
data = d
assert cluster_function
# cluster
clusterer = cluster_function(**kwargs).fit(data)
tl = l
cl = clusterer.labels_
# for each cluster containing an FRB candidate, calculate its homogenity
# defined as number of FRB candidates in that cluster/total number of candidates in that cluster
# this is to favor clusters which just have FRB and less RFI excluding unclustered candidates
# total homogenity is the weighted mean of all homogenities
# weighted by number of candidates in that cluster
# excludes unclustered candidates
cluster_labels_frb = np.array(list(set(cl[tl == 1])))
nfrb_cands = (tl == 1).sum()
nfrb_c = 0 # total number of frbs in frb clusters
ntot_c = 0 # total number of candidates in frb clusters
for cluster in cluster_labels_frb:
if cluster == -1:
continue
indexes = np.where(cl == cluster)[0]
groundtruth_labels = np.take(tl, indexes)
ntot = len(groundtruth_labels)
nfrb = (groundtruth_labels == 1).sum()
ntot_c += ntot
nfrb_c += nfrb
if ntot_c == 0:
assert len(cluster_labels_frb) == 1
assert cluster_labels_frb[0] == -1
homogenity_frbs = 0
else:
homogenity_frbs = nfrb_c / ntot_c
# for each cluster containing an FRB candidate, calculate its completeness.
# defined as number of frbs in that cluster/total number of FRBs
# total completeness is the weighted mean of all completeness
# this is to ensure minimum number of FRB clusters
# weighted by number of candidates in that cluster
# includes unclustered candidates
c = 0 # completeness for FRB clusters
ntot_c = 0
for cluster in cluster_labels_frb:
indexes = np.where(cl == cluster)[0]
groundtruth_labels = np.take(tl, indexes)
ntot = len(groundtruth_labels)
nfrb = (groundtruth_labels == 1).sum()
ntot_c += ntot
c += nfrb * ntot
completenes_frbs = c / (nfrb_cands * ntot_c)
# v measure is the harmonic mean of homogenity and completeness to make
# sure that both are high and weighted equally
v_measure = 2 * homogenity_frbs * completenes_frbs / (completenes_frbs +
homogenity_frbs)
if debug:
print(f'Homogenity of FRBs is {homogenity_frbs}')
print(f'Completeness of FRBs is {completenes_frbs}')
print(f'Harmonic mean of these two is {v_measure}')
if plot:
plot_data(data, cl, s)
true_labels = tl
cluster_labels = cl
# check if the FRB candidate is recovered or not (after taking the max snr element of each cluster)
clusters = cluster_labels
cl_rank = np.zeros(len(clusters), dtype=int)
cl_count = np.zeros(len(clusters), dtype=int)
for cluster in np.unique(clusters):
clusterinds = np.where(clusters == cluster)[0]
snrs = s[clusterinds]
cl_rank[clusterinds] = np.argsort(np.argsort(snrs)[::-1]) + 1
cl_count[clusterinds] = len(clusterinds)
# rank one is the highest snr candidate of the cluster
calcinds = np.unique(np.where(cl_rank == 1)[0])
# i think if this contains 1 i.e FRB candidate, that means that FRB wasn't missed,
# and some FRB plots will be generated
# Take indexes of rank 1 candididates (from calcinds) in true_labels, and see if
# label 1 is in there. If yes, then FRB candidate will pass through in one
# or more clusters
if (np.take(true_labels, calcinds) == 1).sum() > 0:
frb_found = True
else:
frb_found = False
return len(
true_labels), frb_found, homogenity_frbs, completenes_frbs, v_measure
