def __init__(self,
kernel_size=1,
stride=1,
pad_mode="valid"):
super(AvgPool2d, self).__init__(kernel_size, stride, pad_mode)
self.avg_pool = P.AvgPool(ksize=self.kernel_size,
strides=self.stride,
padding=self.pad_mode)
def __init__(self,
kernel_size=1,
stride=1,
pad_mode="valid",
data_format="NCHW"):
super(AvgPool2d, self).__init__(kernel_size, stride, pad_mode, data_format)
self.avg_pool = P.AvgPool(ksize=self.kernel_size,
strides=self.stride,
padding=self.pad_mode,
data_format=self.format)
def __init__(self,
kernel_size=1,
stride=1,
pad_mode="valid"):
super(AvgPool1d, self).__init__(kernel_size, stride, pad_mode)
validator.check_value_type('kernel_size', kernel_size, [int], self.cls_name)
validator.check_value_type('stride', stride, [int], self.cls_name)
self.pad_mode = validator.check_string('pad_mode', pad_mode.upper(), ['VALID', 'SAME'], self.cls_name)
validator.check_integer("kernel_size", kernel_size, 1, Rel.GE, self.cls_name)
validator.check_integer("stride", stride, 1, Rel.GE, self.cls_name)
self.kernel_size = (1, kernel_size)
self.stride = (1, stride)
self.avg_pool = P.AvgPool(ksize=self.kernel_size,
strides=self.stride,
padding=self.pad_mode)
self.shape = F.shape
self.reduce_mean = P.ReduceMean(keep_dims=True)
self.slice = P.Slice()
self.expand = P.ExpandDims()
def __init__(self,
block,
layer_nums,
in_channels,
out_channels,
strides,
num_classes):
super(ResNet, self).__init__()
if not len(layer_nums) == len(in_channels) == len(out_channels) == 4:
raise ValueError("the length of layer_num, in_channels, out_channels list must be 4!")
input_data_channel = 4
if format_ == "NCHW":
input_data_channel = 3
self.conv1 = _conv7x7(input_data_channel, 64, stride=2)
self.bn1 = _bn(64)
self.relu = P.ReLU()
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, pad_mode="same", data_format=format_)
self.layer1 = self._make_layer(block,
layer_nums[0],
in_channel=in_channels[0],
out_channel=out_channels[0],
stride=strides[0])
self.layer2 = self._make_layer(block,
layer_nums[1],
in_channel=in_channels[1],
out_channel=out_channels[1],
stride=strides[1])
self.layer3 = self._make_layer(block,
layer_nums[2],
in_channel=in_channels[2],
out_channel=out_channels[2],
stride=strides[2])
self.layer4 = self._make_layer(block,
layer_nums[3],
in_channel=in_channels[3],
out_channel=out_channels[3],
stride=strides[3])
self.avg_pool = P.AvgPool(7, 1, data_format=format_)
self.flatten = nn.Flatten()
self.end_point = _fc(out_channels[3], num_classes)
def __init__(self, kernel_size=1, stride=1, pad_mode="VALID", padding=0):
avg_pool = P.AvgPool(ksize=kernel_size,
strides=stride,
padding=pad_mode)
super(AvgPool2d, self).__init__(kernel_size, stride, pad_mode, padding,
avg_pool)
'skip': ['backward']}),
('Sigmoid', {
'block': P.Sigmoid(),
'desc_inputs': [[1, 3, 4, 4]],
'desc_bprop': [[1, 3, 4, 4]]}),
('MaxPool', {
'block': P.MaxPool(ksize=(2, 2), strides=(2, 2), padding="VALID"),
'desc_inputs': [[100, 3, 28, 28]],
'desc_bprop': [[100, 3, 14, 14]]}),
('MaxPoolGrad', {
'block': G.MaxPoolGrad(ksize=(2, 2), strides=(2, 2), padding="VALID"),
'desc_inputs': [[3, 4, 6, 6], [3, 4, 3, 3], [3, 4, 3, 3]],
'desc_bprop': [[3, 4, 6, 6]],
'skip': ['backward']}),
('AvgPool', {
'block': P.AvgPool(ksize=(2, 2), strides=(2, 2), padding="VALID"),
'desc_inputs': [[100, 3, 28, 28]],
'desc_bprop': [[100, 3, 14, 14]]}),
('AvgPoolGrad', {
'block': G.AvgPoolGrad(ksize=(2, 2), strides=(2, 2), padding="VALID"),
'desc_const': [(3, 4, 6, 6)],
'const_first': True,
'desc_inputs': [[3, 4, 6, 6]],
'desc_bprop': [[3, 4, 6, 6]],
'skip': ['backward']}),
('MaxPoolWithArgmax', {
'block': P.MaxPoolWithArgmax(ksize=2, strides=2),
'desc_inputs': [[128, 32, 32, 64]],
'desc_bprop': [[128, 32, 8, 16], [128, 32, 8, 16]]}),
('SoftmaxCrossEntropyWithLogits', {
'block': P.SoftmaxCrossEntropyWithLogits(),
'desc_inputs': [Tensor(np.ones([1, 1, 32]).astype(np.float32))],
'skip': ['backward']
}),
# rank of x is not 4
('MaxPool2', {
'block': (P.MaxPool(ksize=50, strides=1), {
'exception': ValueError,
'error_keywords': ['MaxPool']
}),
'desc_inputs': [Tensor(np.ones([1, 1, 32, 32]).astype(np.float32))],
'skip': ['backward']
}),
# input is scalar
('AvgPool0', {
'block': (P.AvgPool(), {
'exception': TypeError,
'error_keywords': ['AvgPool']
}),
'desc_inputs': [5.0],
'skip': ['backward']
}),
# rank of x is not 4
('AvgPool1', {
'block': (P.AvgPool(), {
'exception': ValueError,
'error_keywords': ['AvgPool']
}),
'desc_inputs': [Tensor(np.ones([1, 1, 32]).astype(np.float32))],
'skip': ['backward']
}),