def eval(model, split, seq_length, n_cpu, disp):
dataset = GolfDB(data_file='data/val_split_{}.pkl'.format(split),
vid_dir='data/videos_160/',
seq_length=seq_length,
transform=transforms.Compose([ToTensor(),
Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])]),
train=False)
data_loader = DataLoader(dataset,
batch_size=1,
shuffle=False,
num_workers=n_cpu,
drop_last=False)
correct = []
delta = []
tolerance = []
predictions = []
predictions_original = []
ground_truth = []
for i, sample in enumerate(data_loader):
images, labels = sample['images'][:,::step,:,:,:], sample['labels']
# full samples do not fit into GPU memory so evaluate sample in 'seq_length' batches
seq_length_new = int(np.ceil(seq_length/step))
batch = 0
while batch * (seq_length_new-1) < images.shape[1]-1:
if (batch + 1) * (seq_length_new-1) + 1 > images.shape[1]:
image_batch = images[:, batch * (seq_length_new-1):, :, :, :]
else:
image_batch = images[:, batch * (seq_length_new-1):(batch + 1) * (seq_length_new-1)+1, :, :, :]
logits = model(image_batch.to(device))
if batch == 0:
probs = F.softmax(logits.data, dim=1).cpu().numpy()
else:
probs = np.append(probs[:-1], F.softmax(logits.data, dim=1).cpu().numpy(), 0)
batch += 1
gt, pp, deltas, tol, c, original = correct_preds(probs, labels.squeeze())
if disp:
print(i, c)
correct.append(c)
tolerance.append(tol)
delta.append(deltas)
predictions.append(pp)
ground_truth.append(gt)
predictions_original.append(original)
np.savez_compressed('results/' + version_name + '.npz', array1=np.array(delta), array2=np.array(predictions),
array3=np.array(tolerance), array4=np.array(ground_truth),
array5=np.array(predictions_original))
print(np.round(np.mean(np.array(correct),0),3))
print(np.round(np.sqrt(np.mean(np.square(np.array(delta)/np.array(tolerance)[:,np.newaxis]),0)),3))
print(np.round(np.std(np.array(delta)/np.array(tolerance)[:,np.newaxis],0),3))
PCE = np.mean(correct)
return PCE
def eval(model, split, seq_length, n_cpu, disp):
dataset = GolfDB(
data_file="data/val_split_{}.pkl".format(split),
vid_dir="data/videos_160/",
seq_length=seq_length,
transform=transforms.Compose([
ToTensor(),
Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
]),
train=False,
)
data_loader = DataLoader(dataset,
batch_size=1,
shuffle=False,
num_workers=n_cpu,
drop_last=False)
correct = []
for i, sample in enumerate(data_loader):
images, labels = sample["images"], sample["labels"]
# full samples do not fit into GPU memory so evaluate sample in 'seq_length' batches
batch = 0
while batch * seq_length < images.shape[1]:
if (batch + 1) * seq_length > images.shape[1]:
image_batch = images[:, batch * seq_length:, :, :, :]
else:
image_batch = images[:, batch * seq_length:(batch + 1) *
seq_length, :, :, :]
logits = model(image_batch.cuda())
if batch == 0:
probs = F.softmax(logits.data, dim=1).cpu().numpy()
else:
probs = np.append(probs,
F.softmax(logits.data, dim=1).cpu().numpy(),
0)
batch += 1
_, _, _, _, c = correct_preds(probs, labels.squeeze())
if disp:
print(i, c)
correct.append(c)
PCE = np.mean(correct)
return PCE
model = EventDetector(pretrain=True,
width_mult=1.,
lstm_layers=1,
lstm_hidden=256,
bidirectional=True,
dropout=False)
freeze_layers(k, model)
model.train()
model.cuda()
dataset = GolfDB(data_file='data/train_split_{}.pkl'.format(split),
vid_dir='data/videos_160/',
seq_length=seq_length,
transform=transforms.Compose([
ToTensor(),
Normalize([0.485, 0.456, 0.406],
[0.229, 0.224, 0.225])
]),
train=True,
noise_level=noise_level)
data_loader = DataLoader(dataset,
batch_size=bs,
shuffle=True,
num_workers=n_cpu,
drop_last=True)
# the 8 golf swing events are classes 0 through 7, no-event is class 8
# the ratio of events to no-events is approximately 1:35 so weight classes accordingly:
weights = torch.FloatTensor(
[1 / 8, 1 / 8, 1 / 8, 1 / 8, 1 / 8, 1 / 8, 1 / 8, 1 / 8,
def myeval(model, split, seq_length, n_cpu, disp, stream_choice=0):
# summaryFile = open("summary_opt_{}.txt".format(split),"w")
videosNum = 0 # 统计验证集的视频数量
if cfg.FRAME_13_OPEN:
dataset = GolfDB_13(data_file=cfg.OUR_PKL_FILE_PATH,
json_dir=cfg.VAL_JSON_PATH,
dataloader_opt=cfg.DATAOPT,
seq_length=64,
train=False)
else:
if stream_choice == 1:
# 评价非光流法
dataset = GolfDB(
data_file='/home/zqr/codes/GolfDB/data/val_split_{}.pkl'.
format(split),
vid_dir=cfg.VIDEO_160_PATH,
seq_length=seq_length,
transform=None,
myMean=[0.485, 0.456, 0.406],
myStd=[0.229, 0.224, 0.225],
train=False)
else: # 评价光流法
dataset = GolfDB_T(
data_file='/home/zqr/codes/GolfDB/data/val_split_{}.pkl'.
format(split),
vid_dir=cfg.OPT_RESIZE_FILE_PATH,
seq_length=seq_length,
train=False)
data_loader = DataLoader(dataset,
batch_size=1,
shuffle=False,
num_workers=n_cpu,
drop_last=False)
correct = []
# 这三个是为了做融合用
all_probs = []
all_tols = []
all_events = []
for i, sample in enumerate(data_loader):
videosNum += 1
images, labels = sample['images'], sample['labels']
# full samples do not fit into GPU memory so evaluate sample in 'seq_length' batches
batch = 0
while batch * seq_length < images.shape[1]:
if (batch + 1) * seq_length > images.shape[1]:
image_batch = images[:, batch * seq_length:, :, :, :]
else:
image_batch = images[:, batch * seq_length:(batch + 1) *
seq_length, :, :, :]
logits = model(image_batch.cuda())
if batch == 0:
probs = F.softmax(logits.data, dim=1).cpu().numpy()
else:
probs = np.append(probs,
F.softmax(logits.data, dim=1).cpu().numpy(),
0)
batch += 1
events, preds, _, tol, c = correct_preds(probs, labels.squeeze())
all_probs.append(probs)
all_tols.append(tol)
all_events.append(events)
# 统计信息
# for i, item in enumerate(c):
# if c[i] == 0:
# summary[i] += 1
# if c[0] ==0 or c[7]==0:
# info = str((preds - events).tolist())
# summaryFile.write(info)
# summaryFile.write(' ')
# summaryFile.write(tol)
# summaryFile.write('\n')
# else:
# summaryFile.write('\n')
if disp:
# print(i, c)
print("ground truth:")
print(events)
print("preds:")
print(preds)
correct.append(c)
PFCR = np.mean(correct, axis=0)
PCE = np.mean(correct)
print("PCE:")
print(PCE)
# summaryFile.close()
return PCE, videosNum, all_probs, all_tols, all_events, PFCR
def eval(model, split, seq_length, n_cpu, disp, steps=1):
print("------in function")
if not _video_interpolation:
dataset = GolfDB(data_file='data/val_split_{}.pkl'.format(split),
vid_dir='data/videos_160/',
seq_length=seq_length,
transform=transforms.Compose([
ToTensor(),
Normalize([0.485, 0.456, 0.406],
[0.229, 0.224, 0.225])
]),
train=False)
else:
dataset = GolfDB(data_file='data/val_split_{}.pkl'.format(split),
vid_dir='data/videos_160/'.replace(
'videos_160',
'videos_downsampled_' + str(steps) + 'x'),
seq_length=seq_length,
transform=transforms.Compose([
ToTensor(),
Normalize([0.485, 0.456, 0.406],
[0.229, 0.224, 0.225])
]),
train=False)
steps = 1
data_loader = DataLoader(dataset,
batch_size=1,
shuffle=False,
num_workers=n_cpu,
drop_last=False)
idx_keep = np.arange(0, seq_length, steps)
idx_erase = np.delete(np.arange(0, seq_length), idx_keep)
correct = []
for i, sample in enumerate(data_loader):
images, labels = sample['images'], sample['labels']
if steps > 1:
#### Downsample video (temporally)
images[:,
idx_erase, :, :, :] = images[:,
np.repeat(idx_keep, steps -
1)[:len(idx_erase
)], :, :, :]
# full samples do not fit into GPU memory so evaluate sample in 'seq_length' batches
batch = 0
while batch * seq_length < images.shape[1]:
if (batch + 1) * seq_length > images.shape[1]:
image_batch = images[:, batch * seq_length:, :, :, :]
else:
image_batch = images[:, batch * seq_length:(batch + 1) *
seq_length, :, :, :]
logits = model(image_batch.cuda())
if batch == 0:
probs = F.softmax(logits.data, dim=1).cpu().numpy()
else:
probs = np.append(probs,
F.softmax(logits.data, dim=1).cpu().numpy(),
0)
batch += 1
if i == 176:
print('hello')
_, _, _, _, c = correct_preds(probs, labels.squeeze())
if disp:
print(i, c)
correct.append(c)
PCE = np.mean(correct)
return PCE