"shuffle":
False,
"num_workers":
NUM_WORKERS,
"flatten_inputs":
True,
"flatten_targets":
True,
"multi_target":
True,
}
test_loader = get_coordinate_trajectory_dataset(**test_dataset_args)
# ########## SET UP MODEL ########## #
model = FullyConnectedClassifier(**network_args).to(DEVICE)
model.load_state_dict(
torch.load(
os.path.join(MODEL_LOAD_PATH, "fold_" + str(fold) + ".weights")))
optimizer = optim.Adam(model.parameters(),
lr=LEARNING_RATE,
weight_decay=WEIGHT_DECAY)
loss_function = nn.BCELoss()
# ########## EVALUATE ########## #
test_args = {
"model": model,
"device": DEVICE,
"test_loader": test_loader,
"departure_cameras_path": DEPARTURE_CAMERA_PATH,
"targets_path": TARGETS_PATH,
"fold": fold,
"phase": "test",
"batch_size": BATCH_SIZE,
"shuffle": False,
"num_workers": NUM_WORKERS,
"flatten_inputs": False,
"multi_target": True,
}
test_loader = get_coordinate_trajectory_dataset(**test_dataset_args)
# ########## SET UP MODEL ########## #
encoder = RecurrentEncoder(**encoder_args).to(DEVICE)
decoder = FullyConnectedClassifier(**decoder_args).to(DEVICE)
encoder.load_state_dict(
torch.load(
os.path.join(MODEL_LOAD_PATH,
"encoder_fold_" + str(fold) + ".weights")))
decoder.load_state_dict(
torch.load(
os.path.join(MODEL_LOAD_PATH,
"decoder_fold_" + str(fold) + ".weights")))
loss_function = nn.BCELoss()
# ########## EVALUATE ########## #
test_args = {
"encoder": encoder,
"departure_cameras_path": CROSS_VALIDATION_DEPARTURE_CAMERAS_PATH,
"targets_path": CROSS_VALIDATION_WHEN_TARGETS_PATH,
"fold": fold,
"phase": "test",
"batch_size": BATCH_SIZE,
"shuffle": False,
"num_workers": NUM_WORKERS,
"flatten_inputs": True,
"flatten_targets": True,
}
train_loader = get_coordinate_trajectory_dataset(**train_dataset_args)
val_loader = get_coordinate_trajectory_dataset(**val_dataset_args)
test_loader = get_coordinate_trajectory_dataset(**test_dataset_args)
# ########## SET UP MODEL ########## #
model = FullyConnectedClassifier(**network_args).to(DEVICE)
print(fold, model)
optimizer = optim.Adam(model.parameters(),
lr=LEARNING_RATE,
weight_decay=WEIGHT_DECAY)
loss_function = nn.BCELoss()
# ########## TRAIN AND EVALUATE ########## #
best_ap = 0
for epoch in range(NUM_EPOCHS):
print("----------- EPOCH " + str(epoch) + " -----------")
trainer_args = {
"model": model,
"device": DEVICE,
"targets_path": CROSS_VALIDATION_WHICH_TARGETS_PATH,
"fold": fold,
"phase": "test",
"batch_size": BATCH_SIZE,
"shuffle": False,
"num_workers": NUM_WORKERS,
"flatten_inputs": False,
}
train_loader = get_coordinate_trajectory_dataset(**train_dataset_args)
val_loader = get_coordinate_trajectory_dataset(**val_dataset_args)
test_loader = get_coordinate_trajectory_dataset(**test_dataset_args)
# ########## SET UP MODEL ########## #
encoder = ConvolutionalEncoder(**encoder_args).to(DEVICE)
decoder = FullyConnectedClassifier(**decoder_args).to(DEVICE)
params = list(encoder.parameters()) + list(decoder.parameters())
optimizer = optim.Adam(params, lr=LEARNING_RATE, weight_decay=WEIGHT_DECAY)
loss_function = nn.BCELoss()
# ########## TRAIN AND EVALUATE ########## #
best_ap = 0
for epoch in range(NUM_EPOCHS):
print("----------- EPOCH " + str(epoch) + " -----------")
trainer_args = {
"encoder": encoder,
"decoder": decoder,
"device": DEVICE,