def main(DATASET, LABELS, CLASS_IDS, BATCH_SIZE, ANNOTATION_FILE, SEQ_SIZE=16,
STEP=16, nstrokes=-1, N_EPOCHS=25):
'''
Extract sequence features from AutoEncoder.
Parameters:
-----------
DATASET : str
path to the video dataset
LABELS : str
path containing stroke labels
CLASS_IDS : str
path to txt file defining classes, similar to THUMOS
BATCH_SIZE : int
size for batch of clips
SEQ_SIZE : int
no. of frames in a clip (min. 16 for 3D CNN extraction)
STEP : int
stride for next example. If SEQ_SIZE=16, STEP=8, use frames (0, 15), (8, 23) ...
partition : str
'all' / 'train' / 'test' / 'val' : Videos to be considered
nstrokes : int
partial extraction of features (do not execute for entire dataset)
Returns:
--------
trajectories, stroke_names
'''
###########################################################################
attn_utils.seed_everything(1234)
if not os.path.isdir(log_path):
os.makedirs(log_path)
# Read the strokes
# Divide the highlight dataset files into training, validation and test sets
train_lst, val_lst, test_lst = autoenc_utils.split_dataset_files(DATASET)
print("No. of training videos : {}".format(len(train_lst)))
# extract_of_features(feat_path, DATASET, LABELS, train_lst, val_lst)
features, stroke_names_id = attn_utils.read_feats(feat_path, feat, snames)
# get matrix of features from dictionary (N, vec_size)
vecs = []
for key in sorted(list(features.keys())):
vecs.append(features[key])
vecs = np.vstack(vecs)
vecs[np.isnan(vecs)] = 0
vecs[np.isinf(vecs)] = 0
#fc7 layer output size (4096)
INP_VEC_SIZE = vecs.shape[-1]
print("INP_VEC_SIZE = ", INP_VEC_SIZE)
km_filepath = os.path.join(log_path, km_filename)
# # Uncomment only while training.
if not os.path.isfile(km_filepath+"_C"+str(cluster_size)+".pkl"):
km_model = make_codebook(vecs, cluster_size) #, model_type='gmm')
## # Save to disk, if training is performed
print("Writing the KMeans models to disk...")
pickle.dump(km_model, open(km_filepath+"_C"+str(cluster_size)+".pkl", "wb"))
else:
# Load from disk, for validation and test sets.
km_model = pickle.load(open(km_filepath+"_C"+str(cluster_size)+".pkl", 'rb'))
print("Create numpy one hot representation for train features...")
onehot_feats = create_bovw_onehot(features, stroke_names_id, km_model)
ft_path = os.path.join(log_path, "C"+str(cluster_size)+"_train.pkl")
with open(ft_path, "wb") as fp:
pickle.dump(onehot_feats, fp)
###########################################################################
features_val, stroke_names_id_val = attn_utils.read_feats(feat_path, feat_val,
snames_val)
print("Create numpy one hot representation for val features...")
onehot_feats_val = create_bovw_onehot(features_val, stroke_names_id_val, km_model)
ft_path_val = os.path.join(log_path, "C"+str(cluster_size)+"_val.pkl")
with open(ft_path_val, "wb") as fp:
pickle.dump(onehot_feats_val, fp)
###########################################################################
features_test, stroke_names_id_test = attn_utils.read_feats(feat_path, feat_test,
snames_test)
print("Create numpy one hot representation for test features...")
onehot_feats_test = create_bovw_onehot(features_test, stroke_names_id_test, km_model)
ft_path_test = os.path.join(log_path, "C"+str(cluster_size)+"_test.pkl")
with open(ft_path_test, "wb") as fp:
pickle.dump(onehot_feats_test, fp)
###########################################################################
# Create a Dataset
train_dataset = StrokeFeaturePairsDataset(ft_path, train_lst, DATASET, LABELS, CLASS_IDS,
frames_per_clip=SEQ_SIZE, extracted_frames_per_clip=2,
step_between_clips=STEP, train=True)
val_dataset = StrokeFeaturePairsDataset(ft_path_val, val_lst, DATASET, LABELS, CLASS_IDS,
frames_per_clip=SEQ_SIZE, extracted_frames_per_clip=2,
step_between_clips=STEP, train=False)
# get labels
labs_keys, labs_values = attn_utils.get_cluster_labels(ANNOTATION_FILE)
# created weighted Sampler for class imbalance
samples_weight = attn_utils.get_sample_weights(train_dataset, labs_keys, labs_values,
train_lst)
sampler = WeightedRandomSampler(samples_weight, len(samples_weight))
train_loader = DataLoader(dataset=train_dataset, batch_size=BATCH_SIZE, #shuffle=True,
sampler=sampler, worker_init_fn=np.random.seed(12))
val_loader = DataLoader(dataset=val_dataset, batch_size=BATCH_SIZE, shuffle=False)
data_loaders = {"train": train_loader, "test": val_loader}
num_classes = len(list(set(labs_values)))
###########################################################################
# load model and set loss function
ntokens = cluster_size # the size of vocabulary
emsize = 200 # embedding dimension
nhid = 200 # the dimension of the feedforward network model in nn.TransformerEncoder
nlayers = 2 # the number of nn.TransformerEncoderLayer in nn.TransformerEncoder
nhead = 2 # the number of heads in the multiheadattention models
dropout = 0.2 # the dropout value
model = tt.TransformerModel(ntokens, emsize, nhead, nhid, nlayers, #num_classes,
dropout)
# model = load_weights(model_path, model, N_EPOCHS,
# "S30"+"C"+str(cluster_size)+"_SGD")
# copy the pretrained weights
# Setup the loss fxn
criterion = nn.CrossEntropyLoss()
model.decoder = nn.Linear(model.ninp, num_classes)
initrange = 0.1
model.decoder.bias.data.zero_()
model.decoder.weight.data.uniform_(-initrange, initrange)
model = model.to(device)
print("Params to learn:")
for name, param in model.named_parameters():
if param.requires_grad == True:
print("\t", name)
# # Observe that all parameters are being optimized
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)
# optimizer_ft = torch.optim.SGD(model.parameters(), lr=0.01, momentum=0.9)
#
# # Decay LR by a factor of 0.1 every 7 epochs
scheduler = StepLR(optimizer, step_size=15, gamma=0.1)
# lr = 5.0 # learning rate
# optimizer = torch.optim.SGD(model.parameters(), lr=lr)
# scheduler = torch.optim.lr_scheduler.StepLR(optimizer, 1.0, gamma=0.95)
###########################################################################
# Training the model
start = time.time()
model = train_model(features, stroke_names_id, model, data_loaders, criterion,
optimizer, scheduler, labs_keys, labs_values,
num_epochs=N_EPOCHS)
end = time.time()
# save the best performing model
save_model_checkpoint(log_path, model, N_EPOCHS,
"S"+str(SEQ_SIZE)+"C"+str(cluster_size)+"_SGD")
# Load model checkpoints
model = load_weights(log_path, model, N_EPOCHS,
"S"+str(SEQ_SIZE)+"C"+str(cluster_size)+"_SGD")
print("Total Execution time for {} epoch : {}".format(N_EPOCHS, (end-start)))
###########################################################################
acc = predict(features_val, stroke_names_id_val, model, data_loaders, labs_keys,
labs_values, SEQ_SIZE, phase='test')
###########################################################################
# call count_paramters(model) for displaying total no. of parameters
print("#Parameters : {} ".format(autoenc_utils.count_parameters(model)))
return 0
def main(DATASET,
LABELS,
CLASS_IDS,
BATCH_SIZE,
ANNOTATION_FILE,
SEQ_SIZE=16,
STEP=16,
nstrokes=-1,
N_EPOCHS=25,
base_name=""):
'''
Extract sequence features from AutoEncoder.
Parameters:
-----------
DATASET : str
path to the video dataset
LABELS : str
path containing stroke labels
CLASS_IDS : str
path to txt file defining classes, similar to THUMOS
BATCH_SIZE : int
size for batch of clips
SEQ_SIZE : int
no. of frames in a clip (min. 16 for 3D CNN extraction)
STEP : int
stride for next example. If SEQ_SIZE=16, STEP=8, use frames (0, 15), (8, 23) ...
partition : str
'all' / 'train' / 'test' / 'val' : Videos to be considered
nstrokes : int
partial extraction of features (do not execute for entire dataset)
Returns:
--------
trajectories, stroke_names
'''
###########################################################################
# seed everything
seed = 1234
attn_utils.seed_everything(seed)
if not os.path.isdir(base_name):
os.makedirs(base_name)
# Read the strokes
# Divide the highlight dataset files into training, validation and test sets
train_lst, val_lst, test_lst = autoenc_utils.split_dataset_files(DATASET)
print("No. of training videos : {}".format(len(train_lst)))
###########################################################################
# Create a Dataset
# Clip level transform. Use this with framewiseTransform flag turned off
train_transform = transforms.Compose([
videotransforms.RandomCrop(224),
videotransforms.ToPILClip(),
videotransforms.Resize((112, 112)),
videotransforms.ToTensor(),
videotransforms.Normalize(),
#videotransforms.RandomHorizontalFlip(),\
])
test_transform = transforms.Compose([
videotransforms.CenterCrop(224),
videotransforms.ToPILClip(),
videotransforms.Resize((112, 112)),
videotransforms.ToTensor(),
videotransforms.Normalize(),
#videotransforms.RandomHorizontalFlip(),\
])
train_dataset = CricketStrokesDataset(train_lst,
DATASET,
LABELS,
CLASS_IDS,
frames_per_clip=SEQ_SIZE,
step_between_clips=STEP,
train=True,
framewiseTransform=False,
transform=train_transform)
val_dataset = CricketStrokesDataset(val_lst,
DATASET,
LABELS,
CLASS_IDS,
frames_per_clip=SEQ_SIZE,
step_between_clips=STEP,
train=False,
framewiseTransform=False,
transform=test_transform)
###########################################################################
labs_keys, labs_values = attn_utils.get_cluster_labels(ANNOTATION_FILE)
num_classes = len(list(set(labs_values)))
# created weighted Sampler for class imbalance
if not os.path.isfile(
os.path.join(
base_name, "weights_c" + str(num_classes) + "_" +
str(len(train_dataset)) + ".pkl")):
samples_weight = attn_utils.get_sample_weights(train_dataset,
labs_keys, labs_values,
train_lst)
with open(
os.path.join(
base_name, "weights_c" + str(num_classes) + "_" +
str(len(train_dataset)) + ".pkl"), "wb") as fp:
pickle.dump(samples_weight, fp)
with open(
os.path.join(
base_name, "weights_c" + str(num_classes) + "_" +
str(len(train_dataset)) + ".pkl"), "rb") as fp:
samples_weight = pickle.load(fp)
sampler = WeightedRandomSampler(samples_weight, len(samples_weight))
train_loader = DataLoader(dataset=train_dataset,
batch_size=BATCH_SIZE,
sampler=sampler,
worker_init_fn=np.random.seed(12))
val_loader = DataLoader(dataset=val_dataset,
batch_size=BATCH_SIZE,
shuffle=False)
data_loaders = {"train": train_loader, "test": val_loader}
###########################################################################
# load model and set loss function
encoder = conv_attn_model.Conv3DEncoder(HIDDEN_SIZE, 1, bidirectional)
# encoder = conv_attn_model.Conv3DAttention(HIDDEN_SIZE, num_classes, 1, 196, bidirectional)
decoder = conv_attn_model.Conv3DDecoder(HIDDEN_SIZE, num_classes, 1, 1,
bidirectional)
# decoder = conv_encdec_model.Conv3DDecoder(HIDDEN_SIZE, HIDDEN_SIZE, 1, 196, bidirectional)
# model = attn_model.Encoder(10, 20, bidirectional)
# for ft in model.parameters():
# ft.requires_grad = False
# inp_feat_size = model.fc.in_features
# model.fc = nn.Linear(inp_feat_size, num_classes)
# model = model.to(device)
encoder = encoder.to(device)
decoder = decoder.to(device)
# # load checkpoint:
# Setup the loss fxn
criterion = nn.CrossEntropyLoss()
# criterion = nn.MSELoss()
# # Layers to finetune. Last layer should be displayed
print("Params to learn:")
params_to_update = []
for name, param in encoder.named_parameters():
if param.requires_grad == True:
params_to_update.append(param)
print("Encoder : {}".format(name))
for name, param in decoder.named_parameters():
if param.requires_grad == True:
params_to_update.append(param)
print("Decoder : {}".format(name))
# Observe that all parameters are being optimized
# optimizer_ft = torch.optim.Adam(params_to_update, lr=0.001)
# optimizer_ft = torch.optim.SGD(params_to_update, lr=0.01, momentum=0.9)
encoder_optimizer = torch.optim.SGD(encoder.parameters(),
lr=0.01,
momentum=0.9)
decoder_optimizer = torch.optim.SGD(decoder.parameters(),
lr=0.01,
momentum=0.9)
# decoder_optimizer = None
# Decay LR by a factor of 0.1 every 7 epochs
lr_scheduler = StepLR(encoder_optimizer, step_size=10, gamma=0.1)
# # Observe that all parameters are being optimized
# optimizer_ft = optim.SGD(params_to_update, lr=0.001, momentum=0.9)
# ###########################################################################
# Training the model
start = time.time()
(encoder, decoder) = train_model(encoder,
decoder,
data_loaders,
criterion,
encoder_optimizer,
decoder_optimizer,
lr_scheduler,
labs_keys,
labs_values,
num_epochs=N_EPOCHS)
end = time.time()
# save the best performing model
attn_utils.save_attn_model_checkpoint(base_name, (encoder, decoder),
N_EPOCHS, "SGD")
# Load model checkpoints
encoder, decoder = attn_utils.load_attn_model_checkpoint(
base_name, encoder, decoder, N_EPOCHS, "SGD")
print("Total Execution time for {} epoch : {}".format(
N_EPOCHS, (end - start)))
###########################################################################
# features_val, stroke_names_id_val = attn_utils.read_feats(os.path.join(base_name, ft_dir),
# feat_val, snames_val)
print("Writing prediction dictionary....")
pred_out_dict, acc = predict(encoder,
decoder,
data_loaders,
criterion,
labs_keys,
labs_values,
phase='test')
with open(os.path.join(base_name, "pred_dict.pkl"), "wb") as fp:
pickle.dump(pred_out_dict, fp)
# save the output wts and related information
print("#Parameters Encoder : {} ".format(
autoenc_utils.count_parameters(encoder)))
print("#Parameters Decoder : {} ".format(
autoenc_utils.count_parameters(decoder)))
return encoder, decoder
def main(DATASET,
LABELS,
CLASS_IDS,
BATCH_SIZE,
ANNOTATION_FILE,
SEQ_SIZE=16,
STEP=16,
nstrokes=-1,
N_EPOCHS=25,
base_name=""):
'''
Extract sequence features from AutoEncoder.
Parameters:
-----------
DATASET : str
path to the video dataset
LABELS : str
path containing stroke labels
CLASS_IDS : str
path to txt file defining classes, similar to THUMOS
BATCH_SIZE : int
size for batch of clips
SEQ_SIZE : int
no. of frames in a clip (min. 16 for 3D CNN extraction)
STEP : int
stride for next example. If SEQ_SIZE=16, STEP=8, use frames (0, 15), (8, 23) ...
partition : str
'all' / 'train' / 'test' / 'val' : Videos to be considered
nstrokes : int
partial extraction of features (do not execute for entire dataset)
Returns:
--------
trajectories, stroke_names
'''
if not os.path.isdir(base_name):
os.makedirs(base_name)
seed = 1234
attn_utils.seed_everything(seed)
###########################################################################
# Read the strokes
# Divide the highlight dataset files into training, validation and test sets
train_lst, val_lst, test_lst = autoenc_utils.split_dataset_files(DATASET)
print("No. of training videos : {}".format(len(train_lst)))
###########################################################################
# Create a Dataset
# Clip level transform. Use this with framewiseTransform flag turned off
train_transforms = transforms.Compose([
videotransforms.RandomCrop(300),
videotransforms.ToPILClip(),
videotransforms.Resize((112, 112)),
videotransforms.ToTensor(),
videotransforms.Normalize(),
# videotransforms.ScaledNormMinMax(),
])
test_transforms = transforms.Compose([
videotransforms.CenterCrop(300),
videotransforms.ToPILClip(),
videotransforms.Resize((112, 112)),
videotransforms.ToTensor(),
videotransforms.Normalize(),
# videotransforms.ScaledNormMinMax(),
])
train_dataset = CricketStrokesDataset(train_lst,
DATASET,
LABELS,
CLASS_IDS,
frames_per_clip=SEQ_SIZE,
step_between_clips=STEP,
train=True,
framewiseTransform=False,
transform=train_transforms)
val_dataset = CricketStrokesDataset(val_lst,
DATASET,
LABELS,
CLASS_IDS,
frames_per_clip=SEQ_SIZE,
step_between_clips=STEP,
train=False,
framewiseTransform=False,
transform=test_transforms)
###########################################################################
labs_keys, labs_values = attn_utils.get_cluster_labels(ANNOTATION_FILE)
num_classes = len(list(set(labs_values)))
# created weighted Sampler for class imbalance
if not os.path.isfile(
os.path.join(
base_name, "weights_c" + str(num_classes) + "_" +
str(len(train_dataset)) + ".pkl")):
samples_weight = attn_utils.get_sample_weights(train_dataset,
labs_keys, labs_values,
train_lst)
with open(
os.path.join(
base_name, "weights_c" + str(num_classes) + "_" +
str(len(train_dataset)) + ".pkl"), "wb") as fp:
pickle.dump(samples_weight, fp)
with open(
os.path.join(
base_name, "weights_c" + str(num_classes) + "_" +
str(len(train_dataset)) + ".pkl"), "rb") as fp:
samples_weight = pickle.load(fp)
sampler = WeightedRandomSampler(samples_weight, len(samples_weight))
train_loader = DataLoader(dataset=train_dataset,
batch_size=BATCH_SIZE,
sampler=sampler,
worker_init_fn=np.random.seed(12))
val_loader = DataLoader(dataset=val_dataset,
batch_size=BATCH_SIZE,
shuffle=False)
data_loaders = {"train": train_loader, "test": val_loader}
###########################################################################
# load model and set loss function
model = conv_attn_model.C3DGRUv2Orig(HIDDEN_SIZE, 1, num_classes,
bidirectional)
model_pretrained = c3d.C3D()
model_pretrained.load_state_dict(
torch.load("../localization_rnn/" + wts_path))
# model_pretrained = c3d_pre.C3D()
# model_pretrained.fc8 = nn.Linear(4096, 5)
# model_pretrained.load_state_dict(torch.load(pretrained_c3d_wts))
copy_pretrained_weights(model_pretrained, model)
# reset the last layer (default requires_grad is True)
# model.conv5b = nn.Conv3d(512, 512, kernel_size=(3, 3, 3), padding=(1, 1, 1))
# for ft in model.parameters():
# ft.requires_grad = False
# inp_feat_size = model.fc.in_features
# model.fc = nn.Linear(inp_feat_size, num_classes)
model = model.to(device)
# Setup the loss fxn
criterion = nn.CrossEntropyLoss()
# criterion = nn.MSELoss()
# # Layers to finetune. Last layer should be displayed
print("Params to learn:")
params_to_update = []
for name, param in model.named_parameters():
if param.requires_grad == True:
params_to_update.append(param)
print("\t {}".format(name))
# Observe that all parameters are being optimized
# optimizer_ft = torch.optim.Adam(params_to_update, lr=0.01)
optimizer_ft = optim.SGD(params_to_update, lr=0.001, momentum=0.9)
# Decay LR by a factor of 0.1 every 7 epochs
lr_scheduler = StepLR(optimizer_ft, step_size=30, gamma=0.1)
###########################################################################
# Training the model
start = time.time()
model = train_model(model,
data_loaders,
criterion,
optimizer_ft,
lr_scheduler,
labs_keys,
labs_values,
num_epochs=N_EPOCHS)
end = time.time()
# save the best performing model
attn_utils.save_model_checkpoint(base_name, model, N_EPOCHS,
"SGD_c8_c3dgruEp60Step30")
# Load model checkpoints
model = attn_utils.load_weights(base_name, model, N_EPOCHS,
"SGD_c8_c3dgruEp60Step30")
print("Total Execution time for {} epoch : {}".format(
N_EPOCHS, (end - start)))
# ###########################################################################
print("Predicting ...")
acc = predict(model, data_loaders, labs_keys, labs_values, phase='test')
print("#Parameters : {} ".format(autoenc_utils.count_parameters(model)))
return model
def main(DATASET,
LABELS,
CLASS_IDS,
BATCH_SIZE,
ANNOTATION_FILE,
SEQ_SIZE=16,
STEP=16,
nstrokes=-1,
N_EPOCHS=25):
'''
Extract sequence features from AutoEncoder.
Parameters:
-----------
DATASET : str
path to the video dataset
LABELS : str
path containing stroke labels
CLASS_IDS : str
path to txt file defining classes, similar to THUMOS
BATCH_SIZE : int
size for batch of clips
SEQ_SIZE : int
no. of frames in a clip (min. 16 for 3D CNN extraction)
STEP : int
stride for next example. If SEQ_SIZE=16, STEP=8, use frames (0, 15), (8, 23) ...
partition : str
'all' / 'train' / 'test' / 'val' : Videos to be considered
nstrokes : int
partial extraction of features (do not execute for entire dataset)
Returns:
--------
trajectories, stroke_names
'''
###########################################################################
attn_utils.seed_everything(1234)
if not os.path.isdir(log_path):
os.makedirs(log_path)
# Read the strokes
# Divide the highlight dataset files into training, validation and test sets
train_lst, val_lst, test_lst = autoenc_utils.split_dataset_files(DATASET)
print("No. of training videos : {}".format(len(train_lst)))
features, stroke_names_id = attn_utils.read_feats(feat_path, feat, snames)
features2, stroke_names_id2 = attn_utils.read_feats(
feat_path2, feat2, snames2)
# get matrix of features from dictionary (N, vec_size)
vecs, vecs2 = [], []
for key in stroke_names_id:
vecs.append(features[key])
vecs2.append(features2[key])
vecs, vecs2 = np.vstack(vecs), np.vstack(vecs2)
vecs[np.isnan(vecs)] = 0
vecs[np.isinf(vecs)] = 0
vecs2[np.isnan(vecs2)] = 0
vecs2[np.isinf(vecs2)] = 0
# vecs = traj_utils.apply_PCA(vecs, 10)
# vecs2 = traj_utils.apply_PCA(vecs2, 10)
# form_lower_dim_dict(features, stroke_names_id, vecs)
# form_lower_dim_dict(features2, stroke_names_id2, vecs2)
#fc7 layer output size (4096)
INP_VEC_SIZE, INP_VEC_SIZE2 = vecs.shape[-1], vecs2.shape[-1]
print("INP_VEC_SIZE = {} : INP_VEC_SIZE2 = {}".format(
INP_VEC_SIZE, INP_VEC_SIZE2))
km_filepath = os.path.join(log_path, km_filename)
# Feats1
if not os.path.isfile(km_filepath + "_C" + str(cluster_size) + ".pkl"):
km_model = make_codebook(vecs, cluster_size) #, model_type='gmm')
## # Save to disk, if training is performed
print("Writing the KMeans models to disk...")
pickle.dump(
km_model,
open(km_filepath + "_C" + str(cluster_size) + ".pkl", "wb"))
else:
# Load from disk, for validation and test sets.
km_model = pickle.load(
open(km_filepath + "_C" + str(cluster_size) + ".pkl", 'rb'))
# Feats2
if not os.path.isfile(km_filepath + "_C" + str(cluster_size) + "_2.pkl"):
km_model2 = make_codebook(vecs2, cluster_size) #, model_type='gmm')
## # Save to disk, if training is performed
print("Writing the KMeans models to disk...")
pickle.dump(
km_model2,
open(km_filepath + "_C" + str(cluster_size) + "_2.pkl", "wb"))
else:
# Load from disk, for validation and test sets.
km_model2 = pickle.load(
open(km_filepath + "_C" + str(cluster_size) + "_2.pkl", 'rb'))
print("Create numpy one hot representation for train features...")
onehot_feats = create_bovw_SA(features, stroke_names_id, km_model)
print("Create numpy one hot representation for train features2...")
onehot_feats2 = create_bovw_SA(features2, stroke_names_id2, km_model2)
ft_path = os.path.join(log_path,
"onehot_C" + str(cluster_size) + "_train.pkl")
ft_path2 = os.path.join(log_path,
"onehot_C" + str(cluster_size) + "_train_2.pkl")
with open(ft_path, "wb") as fp:
pickle.dump(onehot_feats, fp)
with open(ft_path2, "wb") as fp:
pickle.dump(onehot_feats2, fp)
###########################################################################
features_val, stroke_names_id_val = attn_utils.read_feats(
feat_path, feat_val, snames_val)
features_val2, stroke_names_id_val2 = attn_utils.read_feats(
feat_path2, feat_val2, snames_val2)
# # get matrix of features from dictionary (N, vec_size)
# vecs, vecs2 = [], []
# for key in stroke_names_id:
# vecs.append(features[key])
# vecs2.append(features2[key])
# vecs, vecs2 = np.vstack(vecs), np.vstack(vecs2)
#
# vecs[np.isnan(vecs)] = 0
# vecs[np.isinf(vecs)] = 0
# vecs2[np.isnan(vecs2)] = 0
# vecs2[np.isinf(vecs2)] = 0
#
# form_lower_dim_dict(features, stroke_names_id, vecs)
# form_lower_dim_dict(features2, stroke_names_id2, vecs2)
print("Create numpy one hot representation for val features...")
onehot_feats_val = create_bovw_SA(features_val, stroke_names_id_val,
km_model)
print("Create numpy one hot representation for val features2...")
onehot_feats_val2 = create_bovw_SA(features_val2, stroke_names_id_val2,
km_model2)
ft_path_val = os.path.join(log_path,
"onehot_C" + str(cluster_size) + "_val.pkl")
ft_path_val2 = os.path.join(log_path,
"onehot_C" + str(cluster_size) + "_val_2.pkl")
with open(ft_path_val, "wb") as fp:
pickle.dump(onehot_feats_val, fp)
with open(ft_path_val2, "wb") as fp:
pickle.dump(onehot_feats_val2, fp)
###########################################################################
# Create a Dataset
# ft_path = os.path.join(base_name, ft_dir, feat)
train_dataset = StrokeFeatureSequencesDataset(ft_path,
ft_path2,
train_lst,
DATASET,
LABELS,
CLASS_IDS,
frames_per_clip=SEQ_SIZE,
extracted_frames_per_clip=2,
step_between_clips=STEP,
train=True)
# ft_path_val = os.path.join(base_name, ft_dir, feat_val)
val_dataset = StrokeFeatureSequencesDataset(ft_path_val,
ft_path_val2,
val_lst,
DATASET,
LABELS,
CLASS_IDS,
frames_per_clip=SEQ_SIZE,
extracted_frames_per_clip=2,
step_between_clips=STEP,
train=False)
# get labels
labs_keys, labs_values = attn_utils.get_cluster_labels(ANNOTATION_FILE)
# created weighted Sampler for class imbalance
samples_weight = attn_utils.get_sample_weights(train_dataset, labs_keys,
labs_values, train_lst)
sampler = WeightedRandomSampler(samples_weight, len(samples_weight))
train_loader = DataLoader(dataset=train_dataset,
batch_size=BATCH_SIZE,
sampler=sampler,
worker_init_fn=np.random.seed(12))
val_loader = DataLoader(dataset=val_dataset,
batch_size=BATCH_SIZE,
shuffle=False)
data_loaders = {"train": train_loader, "test": val_loader}
num_classes = len(list(set(labs_values)))
# vis_clusters(features, onehot_feats, stroke_names_id, 2, DATASET, log_path)
###########################################################################
# load model and set loss function
model = attn_model.GRUBoWMultiStreamClassifier(INPUT_SIZE, INPUT_SIZE,
HIDDEN_SIZE, HIDDEN_SIZE,
num_classes, N_LAYERS,
bidirectional)
# model = load_weights(base_name, model, N_EPOCHS, "Adam")
# for ft in model.parameters():
# ft.requires_grad = False
# Setup the loss fxn
criterion = nn.CrossEntropyLoss()
model = model.to(device)
print("Params to learn:")
params_to_update = []
for name, param in model.named_parameters():
if param.requires_grad == True:
params_to_update.append(param)
# print("\t",name)
# Observe that all parameters are being optimized
optimizer_ft = torch.optim.Adam(model.parameters(), lr=0.001)
# optimizer_ft = torch.optim.SGD(model.parameters(), lr=0.01, momentum=0.9)
# Decay LR by a factor of 0.1 every 7 epochs
exp_lr_scheduler = StepLR(optimizer_ft, step_size=15, gamma=0.1)
###########################################################################
# Training the model
start = time.time()
model = train_model(features,
stroke_names_id,
model,
data_loaders,
criterion,
optimizer_ft,
exp_lr_scheduler,
labs_keys,
labs_values,
num_epochs=N_EPOCHS)
end = time.time()
#
# # save the best performing model
attn_utils.save_model_checkpoint(
log_path, model, N_EPOCHS,
"S" + str(SEQ_SIZE) + "C" + str(cluster_size) + "_SGD")
# Load model checkpoints
model = attn_utils.load_weights(
log_path, model, N_EPOCHS,
"S" + str(SEQ_SIZE) + "C" + str(cluster_size) + "_SGD")
print("Total Execution time for {} epoch : {}".format(
N_EPOCHS, (end - start)))
# ###########################################################################
acc = predict(features_val,
stroke_names_id_val,
model,
data_loaders,
labs_keys,
labs_values,
SEQ_SIZE,
phase='test')
# call count_paramters(model) for displaying total no. of parameters
print("#Parameters : {} ".format(autoenc_utils.count_parameters(model)))
return acc
def main(DATASET,
LABELS,
CLASS_IDS,
BATCH_SIZE,
ANNOTATION_FILE,
SEQ_SIZE=16,
STEP=16,
nstrokes=-1,
N_EPOCHS=25,
base_name=""):
'''
Extract sequence features from AutoEncoder.
Parameters:
-----------
DATASET : str
path to the video dataset
LABELS : str
path containing stroke labels
CLASS_IDS : str
path to txt file defining classes, similar to THUMOS
BATCH_SIZE : int
size for batch of clips
SEQ_SIZE : int
no. of frames in a clip (min. 16 for 3D CNN extraction)
STEP : int
stride for next example. If SEQ_SIZE=16, STEP=8, use frames (0, 15), (8, 23) ...
partition : str
'all' / 'train' / 'test' / 'val' : Videos to be considered
nstrokes : int
partial extraction of features (do not execute for entire dataset)
Returns:
--------
trajectories, stroke_names
'''
attn_utils.seed_everything(123)
###########################################################################
# Read the strokes
# Divide the highlight dataset files into training, validation and test sets
train_lst, val_lst, test_lst = autoenc_utils.split_dataset_files(DATASET)
print("No. of training videos : {}".format(len(train_lst)))
###########################################################################
# Create a Dataset
# Clip level transform. Use this with framewiseTransform flag turned off
# clip_transform = transforms.Compose([videotransforms.CenterCrop(224),
# videotransforms.ToPILClip(),
# videotransforms.Resize((112, 112)),
## videotransforms.RandomCrop(112),
# videotransforms.ToTensor(),
# videotransforms.Normalize(),
# #videotransforms.RandomHorizontalFlip(),\
# ])
ft_path = os.path.join(base_name, ft_dir, feat)
train_dataset = StrokeFeatureSequenceDataset(ft_path,
train_lst,
DATASET,
LABELS,
CLASS_IDS,
frames_per_clip=SEQ_SIZE,
extracted_frames_per_clip=2,
step_between_clips=STEP,
train=True)
ft_path_val = os.path.join(base_name, ft_dir, feat_val)
val_dataset = StrokeFeatureSequenceDataset(ft_path_val,
test_lst,
DATASET,
LABELS,
CLASS_IDS,
frames_per_clip=SEQ_SIZE,
extracted_frames_per_clip=2,
step_between_clips=STEP,
train=False)
# get labels
labs_keys, labs_values = attn_utils.get_cluster_labels(ANNOTATION_FILE)
# created weighted Sampler for class imbalance
samples_weight = attn_utils.get_sample_weights(train_dataset, labs_keys,
labs_values, train_lst)
sampler = WeightedRandomSampler(samples_weight, len(samples_weight))
train_loader = DataLoader(dataset=train_dataset,
batch_size=BATCH_SIZE,
sampler=sampler)
val_loader = DataLoader(dataset=val_dataset,
batch_size=BATCH_SIZE,
shuffle=False)
data_loaders = {"train": train_loader, "test": val_loader}
num_classes = len(list(set(labs_values)))
###########################################################################
# load model and set loss function
model = attn_model.GRUClassifier(INPUT_SIZE, HIDDEN_SIZE, num_classes,
N_LAYERS, bidirectional)
# model = load_weights(base_name, model, N_EPOCHS, "Adam")
# for ft in model.parameters():
# ft.requires_grad = False
# Setup the loss fxn
criterion = nn.CrossEntropyLoss()
model = model.to(device)
# print("Params to learn:")
params_to_update = []
for name, param in model.named_parameters():
if param.requires_grad == True:
params_to_update.append(param)
# print("\t",name)
# Observe that all parameters are being optimized
# optimizer_ft = torch.optim.Adam(model.parameters(), lr=0.001)
optimizer_ft = torch.optim.SGD(model.parameters(), lr=0.01, momentum=0.9)
# Decay LR by a factor of 0.1 every 7 epochs
exp_lr_scheduler = StepLR(optimizer_ft, step_size=10, gamma=0.1)
features, stroke_names_id = attn_utils.read_feats(
os.path.join(base_name, ft_dir), feat, snames)
###########################################################################
# Training the model
start = time.time()
# model = train_model(features, stroke_names_id, model, data_loaders, criterion,
# optimizer_ft, exp_lr_scheduler, labs_keys, labs_values,
# num_epochs=N_EPOCHS)
end = time.time()
# save the best performing model
# attn_utils.save_model_checkpoint("logs/gru_of20_Hidden512", model, N_EPOCHS,
# "S"+str(SEQ_SIZE)+"_SGD")
# Load model checkpoints
model = attn_utils.load_weights("logs/gru_of20_Hidden512", model, N_EPOCHS,
"S" + str(SEQ_SIZE) + "_SGD")
print("Total Execution time for {} epoch : {}".format(
N_EPOCHS, (end - start)))
# ###########################################################################
features_val, stroke_names_id_val = attn_utils.read_feats(
os.path.join(base_name, ft_dir), feat_val, snames_val)
acc = predict(features_val,
stroke_names_id_val,
model,
data_loaders,
labs_keys,
labs_values,
phase='test')
# call count_paramters(model) for displaying total no. of parameters
print("#Parameters : {} ".format(autoenc_utils.count_parameters(model)))
return acc