return (out == target).float().mean().item()
def f1_score(output, target, epsilon=1e-7):
# turn output into 0-1 map
probas = (output[:, 1, :, :] > 0.).float()
TP = (probas * target).sum(dim=1)
precision = TP / (probas.sum(dim=1) + epsilon)
recall = TP / (target.sum(dim=1) + epsilon)
f1 = 2 * precision * recall / (precision + recall + epsilon)
f1 = f1.clamp(min=epsilon, max=1-epsilon)
return f1.mean().item(), (precision.mean().item(), recall.mean().item())
cc = Configs()
print("Loading stored model")
model = SegnetConvLSTM(cc.hidden_dims, decoder_out_channels=2, lstm_nlayers=len(cc.hidden_dims),
vgg_decoder_config=cc.decoder_config)
tu.load_model_checkpoint(model, '../train-results/model-fixed.torch', inference=False, map_location=device)
model.to(device)
print("Model loaded")
tu_test_dataset = TUSimpleDataset(config.ts_root, config.ts_subdirs, config.ts_flabels, shuffle=False)#, shuffle_seed=9)
# build data loader
tu_test_dataloader = DataLoader(tu_test_dataset, batch_size=cc.test_batch, shuffle=True, num_workers=2)
# using crossentropy for weighted loss
criterion = nn.CrossEntropyLoss(weight=torch.FloatTensor([0.02, 1.02])).to(device)
validate(tu_test_dataloader, model, criterion, log_every=1)
args.add_argument("-m",
'--model-path',
required=True,
type=str,
help='Pre-trained model filepath')
args = args.parse_args()
# load model
cc = Configs()
print("Loading stored model")
model = SegnetConvLSTM(cc.hidden_dims,
decoder_out_channels=2,
lstm_nlayers=len(cc.hidden_dims),
vgg_decoder_config=cc.decoder_config)
model = model.to(device)
tu.load_model_checkpoint(model,
args.model_path,
inference=False,
map_location=device)
print("Model loaded")
# create dataloader
tu_test_dataset = TUSimpleDataset(config.ts_root, config.ts_subdirs,
config.ts_flabels)
tu_dataloader = DataLoader(tu_test_dataset, batch_size=2, shuffle=True)
model.train()
with torch.no_grad():
for batchno, (frames, targets) in enumerate(tu_dataloader):
frames = [f.to(device) for f in frames]
output = model(frames)
targets_ = targets.squeeze(1).long().to(device)
recall = TP / (target.sum(dim=1) + epsilon)
f1 = 2 * precision * recall / (precision + recall + epsilon)
f1 = f1.clamp(min=epsilon, max=1 - epsilon)
return f1.mean().item(), (precision.mean().item(), recall.mean().item())
if __name__ == '__main__':
cc = Configs()
print("Loading stored model")
model = SegnetConvLSTM(cc.hidden_dims,
decoder_out_channels=2,
lstm_nlayers=len(cc.hidden_dims),
vgg_decoder_config=cc.decoder_config)
tu.load_model_checkpoint(model,
'C:/Users/arind/Downloads/model.torch',
inference=False,
map_location=device)
model.to(device)
print("Model loaded")
tu_test_dataset = TUSimpleDataset(config.ts_root,
config.ts_subdirs,
config.ts_flabels,
shuffle=False) #, shuffle_seed=9)
# build data loader
tu_test_dataloader = DataLoader(tu_test_dataset,
batch_size=cc.test_batch,
shuffle=True,
num_workers=1)
import numpy as np
"""
Asses model output quality visually, by plotting
inputs-target-prediction.
"""
if __name__ == '__main__':
# load model
cc = Configs()
print("Loading stored model")
model = SegnetConvLSTM(cc.hidden_dims,
decoder_out_channels=2,
lstm_nlayers=len(cc.hidden_dims),
vgg_decoder_config=cc.decoder_config)
tu.load_model_checkpoint(
model,
'/Volumes/Samsung128/projects/ispr-project/train-results/model-fixed.torch',
inference=False,
map_location=device)
print("Model loaded")
# create dataloader
tu_test_dataset = TUSimpleDataset(config.ts_root, config.ts_subdirs,
config.ts_flabels)
tu_dataloader = DataLoader(tu_test_dataset, batch_size=2, shuffle=True)
model.train()
with torch.no_grad():
for batchno, (frames, targets) in enumerate(tu_dataloader):
output = model(frames)
targets_ = targets.squeeze(1).long()
print(
tu_train_dataloader = DataLoader(tu_tr_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=workers)
# tu_test_dataloader = DataLoader(tu_test_dataset, batch_size=cc.test_batch, shuffle=False, num_workers=4)
# **MODEL**
# output size must have dimension (B, C..), where C = number of classes
model = SegnetConvLSTM(hidden_dims,
decoder_out_channels=2,
lstm_nlayers=len(hidden_dims),
vgg_decoder_config=decoder_config)
if cc.load_model:
trainu.load_model_checkpoint(
model,
'/content/drive/My Drive/model-fixed.torch',
inference=False,
map_location=device)
model.to(device)
# define loss function (criterion) and optimizer
# using crossentropy for weighted loss on background and lane classes
criterion = nn.CrossEntropyLoss(
weight=torch.FloatTensor([0.02, 1.02])).to(device)
# criterion = nn.BCEWithLogitsLoss(pos_weight=torch.FloatTensor([17.])).to(device)
# optimizer = torch.optim.SGD(model.parameters(), lr, momentum=momentum, weight_decay=weight_decay)
optimizer = torch.optim.Adam(model.parameters(),
init_lr) #, weight_decay=weight_decay)
import matplotlib.pyplot as plt
import numpy as np
"""
Asses model output quality visually, by plotting
inputs-target-prediction.
"""
if __name__ == '__main__':
# load model
cc = Configs()
print("Loading stored model")
model = SegnetConvLSTM(cc.hidden_dims,
decoder_out_channels=2,
lstm_nlayers=len(cc.hidden_dims),
vgg_decoder_config=cc.decoder_config)
tu.load_model_checkpoint(model,
'model.torch',
inference=False,
map_location=device)
print("Model loaded")
# create dataloader
tu_test_dataset = TUSimpleDataset(config.ts_root, config.ts_subdirs,
config.ts_flabels)
tu_dataloader = DataLoader(tu_test_dataset, batch_size=2, shuffle=True)
model.train()
with torch.no_grad():
for batchno, (frames, targets) in enumerate(tu_dataloader):
output = model(frames)
targets_ = targets.squeeze(1).long()
print(
"Loss:",