def eval_multidec(args):
print("Evaluate multidec")
device = torch.device(args.gpu)
print("Loading dataset...")
full_dataset = load_multi_csv_data(args, CONFIG)
print("Loading dataset completed")
# full_loader = DataLoader(full_dataset, batch_size=args.batch_size, shuffle=False)
image_encoder = MDEC_encoder(input_dim=args.input_dim, z_dim=args.latent_dim, n_clusters=args.n_clusters,
encodeLayer=[500, 500, 2000], activation="relu", dropout=0)
image_encoder.load_model(os.path.join(CONFIG.CHECKPOINT_PATH, "image_sdae_" + str(args.latent_dim)) + ".pt")
text_encoder = MDEC_encoder(input_dim=args.input_dim, z_dim=args.latent_dim, n_clusters=args.n_clusters,
encodeLayer=[500, 500, 2000], activation="relu", dropout=0)
text_encoder.load_model(os.path.join(CONFIG.CHECKPOINT_PATH, "text_sdae_" + str(args.latent_dim)) + ".pt")
mdec = MultiDEC(device=device, image_encoder=image_encoder, text_encoder=text_encoder)
mdec.load_model(
os.path.join(CONFIG.CHECKPOINT_PATH, "mdec_" + str(args.latent_dim)) + '_' + str(args.n_clusters) + ".pt")
short_codes, y_pred, y_confidence, pvalue = mdec.fit_predict(full_dataset, args.batch_size)
result_df = pd.DataFrame(data={'cluster_id': y_pred, 'confidence': y_confidence}, index=short_codes)
result_df.index.name = "short_code"
result_df.sort_index(inplace=True)
result_df.to_csv(
os.path.join(CONFIG.CSV_PATH, 'multidec_result_' + str(args.latent_dim) + '_' + str(args.n_clusters) + '.csv'),
encoding='utf-8-sig')
pvalue_df = pd.DataFrame(data=pvalue, index=short_codes, columns=[str(i) for i in range(args.n_clusters)])
pvalue_df.index.name = "short_code"
pvalue_df.sort_index(inplace=True)
pvalue_df.to_csv(
os.path.join(CONFIG.CSV_PATH, 'multidec_pvalue_' + str(args.latent_dim) + '_' + str(args.n_clusters) + '.csv'),
encoding='utf-8-sig')
def train_multidec(args):
print("Training multidec")
device = torch.device(args.gpu)
print("Loading dataset...")
full_dataset = load_multi_csv_data(args, CONFIG)
print("Loading dataset completed")
# full_loader = DataLoader(full_dataset, batch_size=args.batch_size, shuffle=False)
image_encoder = MDEC_encoder(input_dim=args.input_dim, z_dim=args.latent_dim, n_clusters=args.n_clusters,
encodeLayer=[500, 500, 2000], activation="relu", dropout=0)
image_encoder.load_model(os.path.join(CONFIG.CHECKPOINT_PATH, "image_sdae_" + str(args.latent_dim)) + ".pt")
text_encoder = MDEC_encoder(input_dim=args.input_dim, z_dim=args.latent_dim, n_clusters=args.n_clusters,
encodeLayer=[500, 500, 2000], activation="relu", dropout=0)
text_encoder.load_model(os.path.join(CONFIG.CHECKPOINT_PATH, "text_sdae_" + str(args.latent_dim)) + ".pt")
mdec = MultiDEC(device=device, image_encoder=image_encoder, text_encoder=text_encoder, n_clusters=args.n_clusters)
exp = Experiment("MDEC " + str(args.latent_dim) + '_' + str(args.n_clusters), capture_io=True)
print(mdec)
for arg, value in vars(args).items():
exp.param(arg, value)
try:
mdec.fit(full_dataset, lr=args.lr, batch_size=args.batch_size, num_epochs=args.epochs,
save_path=CONFIG.CHECKPOINT_PATH)
print("Finish!!!")
finally:
exp.end()
def train_multidec(args):
print("Training multidec")
device = torch.device(args.gpu)
df_image_data = pd.read_csv(os.path.join(CONFIG.CSV_PATH, args.image_csv),
index_col=0,
encoding='utf-8-sig')
df_text_data = pd.read_csv(os.path.join(CONFIG.CSV_PATH, args.text_csv),
index_col=0,
encoding='utf-8-sig')
df_label = pd.read_csv(os.path.join(CONFIG.CSV_PATH, args.label_csv),
index_col=0,
encoding='utf-8-sig')
short_code_array = np.array(df_label.index)
label_array = np.array(df_label['category'])
n_clusters = np.max(label_array) + 1
short_code_train, short_code_val, label_train, label_val = train_test_split(
short_code_array, label_array, test_size=0.2, random_state=42)
df_train = pd.DataFrame(data=label_train,
index=short_code_train,
columns=df_label.columns)
df_val = pd.DataFrame(data=label_val,
index=short_code_val,
columns=df_label.columns)
print("Loading dataset...")
train_dataset, val_dataset = load_multi_csv_data(df_image_data,
df_text_data, df_train,
df_val, CONFIG)
print("Loading dataset completed")
image_encoder = MDEC_encoder(input_dim=args.input_dim,
z_dim=args.latent_dim,
n_clusters=n_clusters,
encodeLayer=[500, 500, 2000],
activation="relu",
dropout=0)
image_encoder.load_model(
os.path.join(CONFIG.CHECKPOINT_PATH, "image_sdae_" +
str(args.latent_dim)) + ".pt")
text_encoder = MDEC_encoder(input_dim=args.input_dim,
z_dim=args.latent_dim,
n_clusters=n_clusters,
encodeLayer=[500, 500, 2000],
activation="relu",
dropout=0)
text_encoder.load_model(
os.path.join(CONFIG.CHECKPOINT_PATH, "text_sdae_" +
str(args.latent_dim)) + ".pt")
mdec = MultiDEC(device=device,
image_encoder=image_encoder,
text_encoder=text_encoder,
n_clusters=n_clusters)
exp = Experiment("MDEC " + str(args.latent_dim), capture_io=True)
print(mdec)
for arg, value in vars(args).items():
exp.param(arg, value)
try:
mdec.fit(train_dataset,
val_dataset,
lr=args.lr,
batch_size=args.batch_size,
num_epochs=args.epochs,
save_path=CONFIG.CHECKPOINT_PATH)
print("Finish!!!")
finally:
exp.end()
def train_multidec(args):
print("Training started")
device = torch.device(args.gpu)
df_image_data = pd.read_csv(os.path.join(CONFIG.CSV_PATH, args.image_csv),
index_col=0,
encoding='utf-8-sig')
df_text_data = pd.read_csv(os.path.join(CONFIG.CSV_PATH, args.text_csv),
index_col=0,
encoding='utf-8-sig')
df_label = pd.read_csv(os.path.join(CONFIG.CSV_PATH, args.label_csv),
index_col=0,
encoding='utf-8-sig')
df_weight = pd.read_csv(os.path.join(CONFIG.CSV_PATH, args.weight_csv),
index_col=0,
encoding='utf-8-sig')
short_code_array = np.array(df_label.index)
label_array = np.array(df_label['category'])
n_classes = np.max(label_array) + 1
exp = Experiment("multi_classifier", capture_io=True)
for arg, value in vars(args).items():
exp.param(arg, value)
try:
kf = KFold(n_splits=5, random_state=42)
image_score_list = []
text_score_list = []
multi_score_list = []
kf_count = 0
for train_index, val_index in kf.split(short_code_array):
print("Current fold: ", kf_count)
short_code_train = short_code_array[train_index]
short_code_val = short_code_array[val_index]
label_train = label_array[train_index]
label_val = label_array[val_index]
df_train = pd.DataFrame(data=label_train,
index=short_code_train,
columns=df_label.columns)
df_val = pd.DataFrame(data=label_val,
index=short_code_val,
columns=df_label.columns)
print("Loading dataset...")
train_dataset, val_dataset = load_multi_csv_data(
df_image_data, df_text_data, df_weight, df_train, df_val,
CONFIG)
print("\nLoading dataset completed")
if args.fixed_weight is None:
image_classifier = SingleClassifier(device=device,
input_dim=args.input_dim,
filter_num=64,
n_classes=n_classes)
text_classifier = SingleClassifier(device=device,
input_dim=args.input_dim,
filter_num=64,
n_classes=n_classes)
print("pretraining image classifier...")
image_classifier.fit(
train_dataset,
val_dataset,
input_modal=1,
lr=args.lr,
num_epochs=args.pretrain_epochs,
save_path=os.path.join(CONFIG.CHECKPOINT_PATH,
"image_classifier") + ".pt")
image_classifier.load_model(
os.path.join(CONFIG.CHECKPOINT_PATH, "image_classifier") +
".pt")
print("pretraining text classifier...")
text_classifier.fit(
train_dataset,
val_dataset,
input_modal=2,
lr=args.lr,
num_epochs=args.pretrain_epochs,
save_path=os.path.join(CONFIG.CHECKPOINT_PATH,
"text_classifier") + ".pt")
text_classifier.load_model(
os.path.join(CONFIG.CHECKPOINT_PATH, "text_classifier") +
".pt")
print("pretraining weight classifier...")
weight_calculator = WeightCalculator(device=device,
input_dim=args.input_dim *
2,
n_classes=n_classes)
weight_calculator.fit(
train_dataset,
val_dataset,
lr=args.lr,
num_epochs=args.pretrain_epochs,
save_path=os.path.join(CONFIG.CHECKPOINT_PATH,
"weight_calculator") + ".pt")
weight_calculator.load_model(
os.path.join(CONFIG.CHECKPOINT_PATH, "weight_calculator") +
".pt")
multi_classifier = MultiClassifier(
device=device,
image_classifier=image_classifier,
text_classifier=text_classifier,
weight_calculator=weight_calculator)
print(multi_classifier)
print("training multi classifier...")
multi_classifier.fit(
train_dataset,
val_dataset,
lr=args.lr,
batch_size=args.batch_size,
num_epochs=args.epochs,
save_path=os.path.join(CONFIG.CHECKPOINT_PATH,
"multi_classifier") + ".pt")
else:
image_classifier = SingleClassifier(device=device,
input_dim=args.input_dim,
filter_num=64,
n_classes=n_classes)
text_classifier = SingleClassifier(device=device,
input_dim=args.input_dim,
filter_num=64,
n_classes=n_classes)
print("pretraining image classifier...")
image_classifier.fit(
train_dataset,
val_dataset,
input_modal=1,
lr=args.lr,
num_epochs=args.pretrain_epochs,
save_path=os.path.join(
CONFIG.CHECKPOINT_PATH, "image_classifier_fw_" +
str(args.fixed_weight)) + ".pt")
image_classifier.load_model(
os.path.join(
CONFIG.CHECKPOINT_PATH, "image_classifier_fw_" +
str(args.fixed_weight)) + ".pt")
print("pretraining text classifier...")
text_classifier.fit(
train_dataset,
val_dataset,
input_modal=2,
lr=args.lr,
num_epochs=args.pretrain_epochs,
save_path=os.path.join(
CONFIG.CHECKPOINT_PATH, "text_classifier_fw_" +
str(args.fixed_weight)) + ".pt")
text_classifier.load_model(
os.path.join(
CONFIG.CHECKPOINT_PATH, "text_classifier_fw_" +
str(args.fixed_weight)) + ".pt")
multi_classifier = MultiClassifier(
device=device,
image_classifier=image_classifier,
text_classifier=text_classifier,
fixed_weight=args.fixed_weight)
print(multi_classifier)
print("training multi classifier with fixed weight...")
multi_classifier.fit(
train_dataset,
val_dataset,
lr=args.lr,
batch_size=args.batch_size,
num_epochs=args.epochs,
save_path=os.path.join(
CONFIG.CHECKPOINT_PATH, "multi_classifier_fw_" +
str(args.fixed_weight)) + ".pt")
print("Finish!!!")
print(
"#current fold best image score: %.6f, text score: %.6f multi score: %.6f"
% (image_classifier.score, text_classifier.score,
multi_classifier.score))
image_score_list.append(image_classifier.score)
text_score_list.append(text_classifier.score)
multi_score_list.append(multi_classifier.score)
kf_count = kf_count + 1
print(
"#average image score: %.6f, text score: %.6f multi score: %.6f" %
(np.mean(image_score_list), np.mean(text_score_list),
np.mean(multi_score_list)))
finally:
exp.end()