def train(net_file,trial_id,resume=None,seed=1234,dropout=[0.5],snapshot_rate=500,
validate_rate=500,num_iter=20000,loss_rate=1,reg=1e-3,mom_init=0.5,
mom_final=0.9,mom_step=0.1,lr_decay=0.95,lr=1e-5,optflow_weight=0):
"""Trains a network described in the file |net| with particular settings.
Args:
net - text file describing network architecture
trial_id - unique integer identifying trial number which corresponds
to the parameter settings
resume - integer indicating iteration from which to resume training
...
Returns:
A tuple of best validation accuracy and the iteration when it occurred.
"""
properties = {}
layers = []
with open(net_file) as fp:
for line in fp:
if line == '\n':
continue
prop, value = line.split(":")
if prop in ('video-shape','train','val','batch-size','name'):
properties[prop] = value.strip().rstrip()
elif prop in ('pool','conv','fc','softmax'):
layers.append((prop,value.rstrip()))
# Assert all necessary fields are present and valid
assert 'name' in properties
assert 'train' in properties
assert 'val' in properties
assert 'batch-size' in properties
try:
properties['batch-size'] = int(properties['batch-size'])
except:
print >> sys.stderr, "batch-size must be an integer"
return None, None
assert 'video-shape' in properties
try:
properties['video-shape'] = \
tuple(int(x) for x in properties['video-shape'] \
.strip('(').rstrip(')').split(','))
except:
print >> sys.stderr, "video-shape not in valid format"
return None, None
# Create directory to store results
savepath = os.path.join("results",properties['name']+"-%04d"%trial_id)
if os.path.isdir(savepath) and resume is None:
print "Attempted to overwrite %s with brand new training." % savepath
print "Training aborted. If you wish to proceed, please delete " \
"%s explicitly, then rerun command" % savepath
return None, None
if not os.path.isdir(savepath):
os.makedirs(savepath)
# Create convnet
net = ConvNet3D(properties['name'],
properties['video-shape'],
properties['batch-size'],
seed=seed)
# Add train / val databases
net.add_train_data(properties['train'])
net.add_val_data(properties['val'])
reg_multipliers = {}
# We will follow convention of naming layers based on how many convolutions
# deep in the architecture they are. For example, a pool layer coming after
# the 6th conv layer will be pool6, even if it isn't the 6th pooling layer.
conv_count = 0
fc_count = 0
for layer_type, value in layers:
if layer_type == "conv":
conv_count += 1
shape, num_filters, reg_mult = value.split()
shape = shape.strip("( )")
shape = tuple(int(x) for x in shape.split(','))
num_filters = int(num_filters)
name = "conv%d"%conv_count
net.add_conv_layer(name, shape, num_filters)
reg_multipliers[name+"_W"] = float(reg_mult.split('=')[1])
if layer_type == "pool":
value = value.strip("( )")
shape = tuple(int(x) for x in value.split(','))
net.add_pool_layer("pool%d"%conv_count,shape)
if layer_type == "fc":
fc_count += 1
num_units_str, reg_mult = value.split()
num_units = int(num_units_str)
p = dropout[min(fc_count,len(dropout))-1]
name = "fc%d"%fc_count
net.add_fc_layer(name,num_units, p)
reg_multipliers[name+"_W"] = float(reg_mult.split('=')[1])
if layer_type == "softmax":
num_classes_str, reg_mult = value.split()
num_classes = int(num_classes_str)
net.add_softmax_layer("softmax",num_classes)
reg_multipliers["softmax_W"] = float(reg_mult.split('=')[1])
snapshot_params = {
"dir": "snapshots",
"rate": snapshot_rate,
"resume": resume}
opt_params = {
"method": "momentum",
"initial": mom_init,
"final": mom_final,
"step": mom_step, # per epoch
"lr_decay": lr_decay,
"lr_base": lr}
reg_params = dict((param,mult*reg) for param,mult in reg_multipliers.items())
# Copy the network architecture description file to the results folder
shutil.copy(net_file,os.path.join(savepath,'architecture.txt'))
solver = Solver(net,reg_params,opt_params)
best_val_accuracy, best_val_iter = solver.train(
num_iter,
snapshot_params,
savepath,
validate_rate=validate_rate,
loss_rate=loss_rate,
optflow_weight=optflow_weight)
return best_val_accuracy, best_val_iter
smallnet.add_conv_layer("conv3", (3, 3, 3), 16)
smallnet.add_pool_layer("pool3", (2, 2, 2))
smallnet.add_conv_layer("conv4", (3, 3, 3), 16)
smallnet.add_pool_layer("pool4", (2, 2, 2))
smallnet.add_fc_layer("fc1", 128, 0.5)
smallnet.add_softmax_layer("softmax", 101)
reg = 5e-3
reg_params = {
"conv1_W": reg,
"conv2_W": reg,
"conv3_W": reg,
"conv4_W": reg,
"fc1_W": reg,
"softmax_W": reg
}
snapshot_params = {"dir": "models/smallnet", "rate": 4000}
opt_params = {
"method": "momentum",
"initial": 0.5,
"final": 0.9,
"step": 0.1, # per epoch
"lr_decay": 0.95,
"lr_base": 1e-5
}
solver = Solver(smallnet, reg_params, opt_params)
solver.train(40000, snapshot_params, validate_rate=4000, loss_rate=1)
smallnet.add_conv_layer("conv3",(3,3,3),16)
smallnet.add_pool_layer("pool3",(2,2,2))
smallnet.add_conv_layer("conv4",(3,3,3),16)
smallnet.add_pool_layer("pool4",(2,2,2))
smallnet.add_fc_layer("fc1",128,0.5)
smallnet.add_softmax_layer("softmax",101)
reg = 5e-3
reg_params = {
"conv1_W": reg,
"conv2_W": reg,
"conv3_W": reg,
"conv4_W": reg,
"fc1_W": reg,
"softmax_W": reg}
snapshot_params = {
"dir": "models/smallnet",
"rate": 4000}
opt_params = {
"method": "momentum",
"initial": 0.5,
"final": 0.9,
"step": 0.1, # per epoch
"lr_decay": 0.95,
"lr_base": 1e-5}
solver = Solver(smallnet,reg_params,opt_params)
solver.train(40000,snapshot_params,validate_rate=4000,loss_rate=1)
