def main(model_dir=None):
netconfig, hyperparams_config, data_config = config()
if model_dir is None:
model_num = int(netconfig['model_dir'][-1]) - 1
model_dir = netconfig['model_dir'][:-1] + str(model_num)
netconfig['model_dir'] = model_dir
train_data, validate_data, test_data = construct_data(netconfig)
def main():
netconfig, _, _ = config()
model = SELUNet(dropout=netconfig["alphadropout"])
netconfig["model_resume_file"] = "model3/saved_models/model_20.pt"
model = load_model(model, netconfig["model_resume_file"])
model.eval()
train_data = AudioDataset("bdl_speech.npz", "bdl_egg.npz",
netconfig["window"], netconfig["window"])
data = [train_data[i] for i in range(10)]
speech = th.cat([d[0] for d in data])
peak_arr = th.cat([d[1] for d in data])
idx = np.random.choice(len(speech), 2000, replace=False)
speech = speech[idx].unsqueeze_(1)
with th.no_grad():
features = model.feature_extractor(speech)
print(f"speech shape {speech.shape} features shape {features.shape}")
features = features.view(features.size(0), -1).numpy()
labels = peak_arr[:, 1][idx].numpy()
features_tsne = TSNE().fit_transform(features)
print(f"features tsne shape {features_tsne.shape}")
positive_idx = labels == 1
negative_idx = labels == 0
print(
f"positive samples: {np.count_nonzero(positive_idx)} negative samples: {np.count_nonzero(negative_idx)}"
)
positive_coords = features_tsne[positive_idx]
negative_coords = features_tsne[negative_idx]
positive_distances = peak_arr[:, 0][idx].numpy()[positive_idx]
bins = np.linspace(0, netconfig["window"], 5)
markers = [".", "v", "^", "*"]
colors = ["b", "r", "k", "m"]
inds = np.digitize(positive_distances, bins)
fig, ax = plt.subplots()
ax.set_title("TSNE L2 plot")
for i, m, c in zip(range(len(bins) - 1), markers, colors):
indices = inds == i
ax.scatter(
positive_coords[indices, 0],
positive_coords[indices, 1],
c=c,
label=f"++ {(bins[i], bins[i+1])}",
marker=m,
)
ax.scatter(negative_coords[:, 0], negative_coords[:, 1], c="g", label="--")
ax.legend(loc=1)
fig.set_tight_layout(True)
ax.set_xlabel("Dimension 1")
ax.set_ylabel("Dimension 2")
mng = plt.get_current_fig_manager()
mng.window.showMaximized()
plt.show()
import os
import time
import copy
import torch
import torch.nn as nn
import torch.nn.functional as F
#from torch.autograd import Variable
from torch.utils.data import DataLoader
import utils
from main import config
from tqdm.auto import tqdm
# base config
args = config()
# normally train & evaluation consistantly going together
def train(dataloaders, model, criterion, optimizer, scheduler, args):
since = time.time()
epochs = args.num_epoch
save_dir = args.save_dir
device = args.device
# best model find
best_model = copy.deepcopy(model.state_dict())
best_acc = 0.0
for epoch in range(epochs):
print(f'Epoch {epoch}/{epochs - 1}')
print()
print(">> Variables:")
print(df[variables])
grid_search = dict(adv_epsilon=[0.01,0.05,0.1,0.5,1.0], adv_norm=['infty', 'l2'])
outputs = ['test_accuracy','adv_accuracy']
epoch = 20
df = pd.DataFrame()
for exp_name, exp_dir in zip(exp_names, exp_dirs):
print(f">> Experiment {exp_name}")
kwargs = load_dict(os.path.join(exp_dir, defaults.ARG_FILE))
args = main.config(**kwargs)
(train_loader, test_loader), device = main.load(args)
models, _, _= main.init(args, device, shape=train_loader.shape)
checkpoints = [os.path.join(exp_dir, fstr(f, args=args))
for f in defaults.SAVE_FILES]
try:
for m,c in zip(models, checkpoints):
m.load_state_dict(torch.load(c))
except:
print(">> Warning: Files missing for {exp_dir}")
continue
for values in itertools.product(*grid_search.values()):
grid = {}
def main():
netconfig, _, _ = config()
model = SELUNet(dropout=netconfig["alphadropout"])
netconfig["model_resume_file"] = "model3/saved_models/model_20.pt"
model = load_model(model, netconfig["model_resume_file"])
model.eval()
train_data = AudioDataset(
"bdl_speech.npz", "bdl_egg.npz", netconfig["window"], netconfig["window"]
)
data = [train_data[i] for i in range(10)]
speech = th.cat([d[0] for d in data])
peak_arr = th.cat([d[1] for d in data])
idx = np.random.choice(len(speech), 2000, replace=False)
speech = speech[idx].unsqueeze_(1)
with th.no_grad():
features = model.feature_extractor(speech)
print(f"speech shape {speech.shape} features shape {features.shape}")
features = features.view(features.size(0), -1).numpy()
labels = peak_arr[:, 1][idx].numpy()
features_tsne = TSNE(perplexity=70, n_iter=2000).fit_transform(features)
print(f"features tsne shape {features_tsne.shape}")
positive_idx = labels == 1
negative_idx = labels == 0
print(
f"positive samples: {np.count_nonzero(positive_idx)} negative samples: {np.count_nonzero(negative_idx)}"
)
positive_coords = features_tsne[positive_idx]
negative_coords = features_tsne[negative_idx]
positive_distances = peak_arr[:, 0][idx].numpy()[positive_idx]
# bins = np.linspace(0, netconfig["window"], 5)
# markers = [".", "v", "^", "*"]
# colors = ["b", "r", "k", "m"]
# inds = np.digitize(positive_distances, bins)
fig, ax = plt.subplots()
# ax.set_title("TSNE L2 plot")
sc = ax.scatter(
positive_coords[:, 0],
positive_coords[:, 1],
c=positive_distances / (netconfig["window"] - 1),
# label=f"++",
marker="o",
cmap="viridis",
)
# ax.scatter(
# negative_coords[:, 0], negative_coords[:, 1], c="g", label="--", marker="."
# )
cbar = plt.colorbar(sc)
cbar.set_ticks([0, 1])
cbar.set_ticklabels(["$1$", "$w_d$"])
# ax.legend(
# ncol=2,
# framealpha=0.2,
# loc="upper center",
# bbox_to_anchor=(0.5, 1.15),
# mode=None,
# markerscale=4,
# )
ax.tick_params(
axis="both",
which="both",
bottom="off",
top="off",
labelbottom="off",
right="off",
left="off",
labelleft="off",
)
fig.set_tight_layout(True)
# ax.set_xlabel("Dimension 1")
# ax.set_ylabel("Dimension 2")
# mng = plt.get_current_fig_manager()
# mng.window.showMaximized()
# plt.show()
model_folder = os.path.join(netconfig["model_resume_file"].split("/")[0], "plots")
os.makedirs(model_folder, exist_ok=True)
curtime = dt.now()
plt.savefig(
os.path.join(
model_folder,
f"fig_{curtime.day}_{curtime.hour}_{curtime.minute}_{curtime.second}.eps",
),
format="eps",
dpi=300,
)