I have been training imagenet2012 with mobilenet_v2.
- I have brought mobilenet_v2 from torchvision.model
from torch import nn
# from .utils import load_state_dict_from_url
print("first")
__all__ = ['MobileNetV2', 'mobilenet_v2']
print("yes")
# model_urls = {
# 'mobilenet_v2': 'https://download.pytorch.org/models/mobilenet_v2-b0353104.pth',
# }
def _make_divisible(v, divisor, min_value=None):
"""
This function is taken from the original tf repo.
It ensures that all layers have a channel number that is divisible by 8
It can be seen here:
https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/mobilenet.py
:param v:
:param divisor:
:param min_value:
:return:
"""
if min_value is None:
min_value = divisor
new_v = max(min_value, int(v + divisor / 2) // divisor * divisor)
# Make sure that round down does not go down by more than 10%.
if new_v < 0.9 * v:
new_v += divisor
return new_v
class ConvBNReLU(nn.Sequential):
def __init__(self, in_planes, out_planes, kernel_size=3, stride=1, groups=1, norm_layer=None):
padding = (kernel_size - 1) // 2
if norm_layer is None:
norm_layer = nn.BatchNorm2d
super(ConvBNReLU, self).__init__(
nn.Conv2d(in_planes, out_planes, kernel_size, stride, padding, groups=groups, bias=False),
norm_layer(out_planes),
nn.ReLU6(inplace=True)
)
class InvertedResidual(nn.Module):
def __init__(self, inp, oup, stride, expand_ratio, norm_layer=None):
super(InvertedResidual, self).__init__()
self.stride = stride
assert stride in [1, 2]
if norm_layer is None:
norm_layer = nn.BatchNorm2d
hidden_dim = int(round(inp * expand_ratio))
self.use_res_connect = self.stride == 1 and inp == oup
layers = []
if expand_ratio != 1:
# pw
layers.append(ConvBNReLU(inp, hidden_dim, kernel_size=1, norm_layer=norm_layer))
layers.extend([
# dw
ConvBNReLU(hidden_dim, hidden_dim, stride=stride, groups=hidden_dim, norm_layer=norm_layer),
# pw-linear
nn.Conv2d(hidden_dim, oup, 1, 1, 0, bias=False),
norm_layer(oup),
])
self.conv = nn.Sequential(*layers)
def forward(self, x):
if self.use_res_connect:
return x + self.conv(x)
else:
return self.conv(x)
class MobileNetV2(nn.Module):
def __init__(self,
num_classes=1000,
width_mult=1.0,
inverted_residual_setting=None,
round_nearest=8,
block=None,
norm_layer=None):
"""
MobileNet V2 main class
Args:
num_classes (int): Number of classes
width_mult (float): Width multiplier - adjusts number of channels in each layer by this amount
inverted_residual_setting: Network structure
round_nearest (int): Round the number of channels in each layer to be a multiple of this number
Set to 1 to turn off rounding
block: Module specifying inverted residual building block for mobilenet
norm_layer: Module specifying the normalization layer to use
"""
super(MobileNetV2, self).__init__()
if block is None:
block = InvertedResidual
if norm_layer is None:
norm_layer = nn.BatchNorm2d
input_channel = 32
last_channel = 1280
if inverted_residual_setting is None:
inverted_residual_setting = [
# t, c, n, s
[1, 16, 1, 1],
[6, 24, 2, 2],
[6, 32, 3, 2],
[6, 64, 4, 2],
[6, 96, 3, 1],
[6, 160, 3, 2],
[6, 320, 1, 1],
]
# only check the first element, assuming user knows t,c,n,s are required
if len(inverted_residual_setting) == 0 or len(inverted_residual_setting[0]) != 4:
raise ValueError("inverted_residual_setting should be non-empty "
"or a 4-element list, got {}".format(inverted_residual_setting))
# building first layer
input_channel = _make_divisible(input_channel * width_mult, round_nearest)
self.last_channel = _make_divisible(last_channel * max(1.0, width_mult), round_nearest)
features = [ConvBNReLU(3, input_channel, stride=2, norm_layer=norm_layer)]
# building inverted residual blocks
for t, c, n, s in inverted_residual_setting:
output_channel = _make_divisible(c * width_mult, round_nearest)
for i in range(n):
stride = s if i == 0 else 1
features.append(block(input_channel, output_channel, stride, expand_ratio=t, norm_layer=norm_layer))
input_channel = output_channel
# building last several layers
features.append(ConvBNReLU(input_channel, self.last_channel, kernel_size=1, norm_layer=norm_layer))
# make it nn.Sequential
self.features = nn.Sequential(*features)
# building classifier
self.classifier = nn.Sequential(
nn.Dropout(0.2),
nn.Linear(self.last_channel, num_classes),
)
# weight initialization
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode='fan_out')
if m.bias is not None:
nn.init.zeros_(m.bias)
elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)):
nn.init.ones_(m.weight)
nn.init.zeros_(m.bias)
elif isinstance(m, nn.Linear):
nn.init.normal_(m.weight, 0, 0.01)
nn.init.zeros_(m.bias)
def _forward_impl(self, x):
# This exists since TorchScript doesn't support inheritance, so the superclass method
# (this one) needs to have a name other than `forward` that can be accessed in a subclass
x = self.features(x)
# Cannot use "squeeze" as batch-size can be 1 => must use reshape with x.shape[0]
x = nn.functional.adaptive_avg_pool2d(x, 1).reshape(x.shape[0], -1)
x = self.classifier(x)
return x
def forward(self, x):
return self._forward_impl(x)
- I have done preprocessing as below code. resize, randomhorizontal flip, normalization
def train_dataloader(self):
train_image_preprocess = transforms.Compose([
transforms.Resize((224,224)),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
])
train_dataset = datasets.ImageNet(
root='imagenet2012',
split='train',
transform=train_image_preprocess)
return DataLoader(train_dataset, batch_size=self.dataset_batch_size,
shuffle=True, persistent_workers=True,
num_workers=8,pin_memory=True)
def val_dataloader(self):
val_image_preprocess = transforms.Compose([
transforms.Resize((224,224)),
transforms.ToTensor(),
transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
])
val_dataset = datasets.ImageNet(
root='imagenet2012',
split='val',
transform=val_image_preprocess)
return DataLoader(val_dataset, batch_size=self.dataset_batch_size,
persistent_workers=True, num_workers=8,
pin_memory=True)
- I have use
loss=nn.CrossEntropyLossas a loss function - used adam optimizer(lr=0.001)
- used reduceLR plateau as scheduler
scheduler = ReduceLROnPlateau(optimizer, mode='min', factor=0.1, patience=10)
but my validation accuracy is still on 61%. Is there any more thing that I have to do in order to receive 71% or above 61% of accuracy? It will be thankful if there is any way to improve my model, becasuse I think this accuracy is not accecptable.