def GroupConv(self, *args, **kwargs):
return brew.group_conv(
self,
*args,
use_cudnn=self.use_cudnn,
order=self.order,
cudnn_exhaustive_search=self.cudnn_exhaustive_search,
ws_nbytes_limit=self.ws_nbytes_limit,
**kwargs)
def GroupConv(self, *args, **kwargs):
return brew.group_conv(
self,
*args,
use_cudnn=self.use_cudnn,
order=self.order,
cudnn_exhaustive_search=self.cudnn_exhaustive_search,
ws_nbytes_limit=self.ws_nbytes_limit,
**kwargs
)
def add_group_conv(self, in_filters, out_filters, kernel, stride=1, pad=0, group=1):
self.comp_idx += 1
self.prev_blob = brew.group_conv(
self.model,
self.prev_blob,
'comp_%d_conv_%d' % (self.comp_count, self.comp_idx),
in_filters,
out_filters,
weight_init=("MSRAFill", {}),
kernel=kernel,
stride=stride,
pad=pad,
no_bias=self.no_bias,
group=group,
)
return self.prev_blob
def _MiniAlexNetNoDropout(self, order):
# First, AlexNet using the cnn wrapper.
model = model_helper.ModelHelper(name="alexnet")
conv1 = brew.conv(
model,
"data",
"conv1",
3,
16,
11,
("XavierFill", {}),
("ConstantFill", {}),
stride=4,
pad=0
)
relu1 = brew.relu(model, conv1, "relu1")
norm1 = brew.lrn(model, relu1, "norm1", size=5, alpha=0.0001, beta=0.75)
pool1 = brew.max_pool(model, norm1, "pool1", kernel=3, stride=2)
conv2 = brew.group_conv(
model,
pool1,
"conv2",
16,
32,
5,
("XavierFill", {}),
("ConstantFill", {"value": 0.1}),
group=2,
stride=1,
pad=2
)
relu2 = brew.relu(model, conv2, "relu2")
norm2 = brew.lrn(model, relu2, "norm2", size=5, alpha=0.0001, beta=0.75)
pool2 = brew.max_pool(model, norm2, "pool2", kernel=3, stride=2)
conv3 = brew.conv(
model,
pool2,
"conv3",
32,
64,
3,
("XavierFill", {'std': 0.01}),
("ConstantFill", {}),
pad=1
)
relu3 = brew.relu(model, conv3, "relu3")
conv4 = brew.group_conv(
model,
relu3,
"conv4",
64,
64,
3,
("XavierFill", {}),
("ConstantFill", {"value": 0.1}),
group=2,
pad=1
)
relu4 = brew.relu(model, conv4, "relu4")
conv5 = brew.group_conv(
model,
relu4,
"conv5",
64,
32,
3,
("XavierFill", {}),
("ConstantFill", {"value": 0.1}),
group=2,
pad=1
)
relu5 = brew.relu(model, conv5, "relu5")
pool5 = brew.max_pool(model, relu5, "pool5", kernel=3, stride=2)
fc6 = brew.fc(
model, pool5, "fc6", 1152, 1024, ("XavierFill", {}),
("ConstantFill", {"value": 0.1})
)
relu6 = brew.relu(model, fc6, "relu6")
fc7 = brew.fc(
model, relu6, "fc7", 1024, 1024, ("XavierFill", {}),
("ConstantFill", {"value": 0.1})
)
relu7 = brew.relu(model, fc7, "relu7")
fc8 = brew.fc(
model, relu7, "fc8", 1024, 5, ("XavierFill", {}),
("ConstantFill", {"value": 0.0})
)
pred = brew.softmax(model, fc8, "pred")
xent = model.LabelCrossEntropy([pred, "label"], "xent")
loss = model.AveragedLoss([xent], ["loss"])
model.AddGradientOperators([loss])
return model