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)
print(
"Loss:",
nn.CrossEntropyLoss(
weight=torch.FloatTensor(cc.loss_weights).to(device))(
output, targets_))
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)
decoded = self.decoder(output, unpool_indices, unpool_sizes)
# return a probability map of the same size of each frame input to the model
return decoded # (NOTE: softmax is applied inside loss for efficiency)
# this won't work if not run in parent directory
if __name__ == '__main__':
root = '/Users/nick/Desktop/train_set/clips/'
subdirs = ['0601', '0531', '0313-1', '0313-2']
flabels = [
'/Users/nick/Desktop/train_set/label_data_0601.json',
'/Users/nick/Desktop/train_set/label_data_0531.json',
'/Users/nick/Desktop/train_set/label_data_0313.json'
]
tu_dataset = TUSimpleDataset(root, subdirs, flabels, shuffle_seed=9)
# build data loader
tu_dataloader = DataLoader(tu_dataset,
batch_size=3,
shuffle=True,
num_workers=2)
model = SegnetConvLSTM()
for batch_no, (list_batched_samples,
batched_targets) in enumerate(tu_dataloader):
with torch.no_grad():
out = model(list_batched_samples)
print(out.size())
if batch_no == 1:
break