modelsummary
modelsummary copied to clipboard
graykode
AttributeError: 'list' object has no attribute 'size'
On running the following code I get the error above
def get_model(**kwargs):
model = models.densenet121(pretrained=True).to(device)
# Freeze parameters so we don't backprop through them
for param in model.parameters():
param.requires_grad = False
model.avgpool = nn.AdaptiveAvgPool2d(output_size=(1,1))
model.classifier = nn.Sequential(nn.Linear(512, 128, 3),
nn.ReLU(),
nn.Dropout(0.2),
nn.Linear(128, 1),
nn.Sigmoid()).to(device)
loss_fn = nn.BCELoss()
optimizer = torch.optim.Adam(model.parameters(), lr=kwargs.get('lr', 1e-3))
return model, loss_fn, optimizer
try:
from modelsummary import summary
except:
!pip install modelsummary
from modelsummary import summary
model, criterion, optimizer = get_model()
summary(model, torch.ones((1,3,IMAGE_SIZE,IMAGE_SIZE)).to(device), show_input=True, show_hierarchical=True)
Somehow it fails after printing an output
DenseNet(
(features): Sequential(
(conv0): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False), 9,408 params
(norm0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 128 params
(relu0): ReLU(inplace=True), 0 params
(pool0): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False), 0 params
(denseblock1): _DenseBlock(
(denselayer1): _DenseLayer(
(norm1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 128 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(64, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 8,192 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 45,440 params
(denselayer2): _DenseLayer(
(norm1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 192 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(96, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 12,288 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 49,600 params
(denselayer3): _DenseLayer(
(norm1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 16,384 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 53,760 params
(denselayer4): _DenseLayer(
(norm1): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 320 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(160, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 20,480 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 57,920 params
(denselayer5): _DenseLayer(
(norm1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 384 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(192, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 24,576 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 62,080 params
(denselayer6): _DenseLayer(
(norm1): BatchNorm2d(224, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 448 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(224, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 28,672 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 66,240 params
), 335,040 params
(transition1): _Transition(
(norm): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 512 params
(relu): ReLU(inplace=True), 0 params
(conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 32,768 params
(pool): AvgPool2d(kernel_size=2, stride=2, padding=0), 0 params
), 33,280 params
(denseblock2): _DenseBlock(
(denselayer1): _DenseLayer(
(norm1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 16,384 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 53,760 params
(denselayer2): _DenseLayer(
(norm1): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 320 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(160, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 20,480 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 57,920 params
(denselayer3): _DenseLayer(
(norm1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 384 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(192, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 24,576 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 62,080 params
(denselayer4): _DenseLayer(
(norm1): BatchNorm2d(224, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 448 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(224, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 28,672 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 66,240 params
(denselayer5): _DenseLayer(
(norm1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 512 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 32,768 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 70,400 params
(denselayer6): _DenseLayer(
(norm1): BatchNorm2d(288, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 576 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(288, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 36,864 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 74,560 params
(denselayer7): _DenseLayer(
(norm1): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 640 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(320, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 40,960 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 78,720 params
(denselayer8): _DenseLayer(
(norm1): BatchNorm2d(352, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 704 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(352, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 45,056 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 82,880 params
(denselayer9): _DenseLayer(
(norm1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 768 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(384, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 49,152 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 87,040 params
(denselayer10): _DenseLayer(
(norm1): BatchNorm2d(416, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 832 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(416, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 53,248 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 91,200 params
(denselayer11): _DenseLayer(
(norm1): BatchNorm2d(448, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 896 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(448, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 57,344 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 95,360 params
(denselayer12): _DenseLayer(
(norm1): BatchNorm2d(480, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 960 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(480, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 61,440 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 99,520 params
), 919,680 params
(transition2): _Transition(
(norm): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 1,024 params
(relu): ReLU(inplace=True), 0 params
(conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False), 131,072 params
(pool): AvgPool2d(kernel_size=2, stride=2, padding=0), 0 params
), 132,096 params
(denseblock3): _DenseBlock(
(denselayer1): _DenseLayer(
(norm1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 512 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 32,768 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 70,400 params
(denselayer2): _DenseLayer(
(norm1): BatchNorm2d(288, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 576 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(288, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 36,864 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 74,560 params
(denselayer3): _DenseLayer(
(norm1): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 640 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(320, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 40,960 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 78,720 params
(denselayer4): _DenseLayer(
(norm1): BatchNorm2d(352, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 704 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(352, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 45,056 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 82,880 params
(denselayer5): _DenseLayer(
(norm1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 768 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(384, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 49,152 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 87,040 params
(denselayer6): _DenseLayer(
(norm1): BatchNorm2d(416, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 832 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(416, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 53,248 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 91,200 params
(denselayer7): _DenseLayer(
(norm1): BatchNorm2d(448, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 896 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(448, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 57,344 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 95,360 params
(denselayer8): _DenseLayer(
(norm1): BatchNorm2d(480, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 960 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(480, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 61,440 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 99,520 params
(denselayer9): _DenseLayer(
(norm1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 1,024 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 65,536 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 103,680 params
(denselayer10): _DenseLayer(
(norm1): BatchNorm2d(544, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 1,088 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(544, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 69,632 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 107,840 params
(denselayer11): _DenseLayer(
(norm1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 1,152 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(576, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 73,728 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 112,000 params
(denselayer12): _DenseLayer(
(norm1): BatchNorm2d(608, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 1,216 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(608, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 77,824 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 116,160 params
(denselayer13): _DenseLayer(
(norm1): BatchNorm2d(640, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 1,280 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(640, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 81,920 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 120,320 params
(denselayer14): _DenseLayer(
(norm1): BatchNorm2d(672, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 1,344 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(672, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 86,016 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 124,480 params
(denselayer15): _DenseLayer(
(norm1): BatchNorm2d(704, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 1,408 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(704, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 90,112 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 128,640 params
(denselayer16): _DenseLayer(
(norm1): BatchNorm2d(736, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 1,472 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(736, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 94,208 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 132,800 params
(denselayer17): _DenseLayer(
(norm1): BatchNorm2d(768, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 1,536 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(768, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 98,304 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 136,960 params
(denselayer18): _DenseLayer(
(norm1): BatchNorm2d(800, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 1,600 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(800, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 102,400 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 141,120 params
(denselayer19): _DenseLayer(
(norm1): BatchNorm2d(832, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 1,664 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(832, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 106,496 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 145,280 params
(denselayer20): _DenseLayer(
(norm1): BatchNorm2d(864, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 1,728 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(864, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 110,592 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 149,440 params
(denselayer21): _DenseLayer(
(norm1): BatchNorm2d(896, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 1,792 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(896, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 114,688 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 153,600 params
(denselayer22): _DenseLayer(
(norm1): BatchNorm2d(928, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 1,856 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(928, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 118,784 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 157,760 params
(denselayer23): _DenseLayer(
(norm1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 1,920 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(960, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 122,880 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 161,920 params
(denselayer24): _DenseLayer(
(norm1): BatchNorm2d(992, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 1,984 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(992, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 126,976 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 166,080 params
), 2,837,760 params
(transition3): _Transition(
(norm): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 2,048 params
(relu): ReLU(inplace=True), 0 params
(conv): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False), 524,288 params
(pool): AvgPool2d(kernel_size=2, stride=2, padding=0), 0 params
), 526,336 params
(denseblock4): _DenseBlock(
(denselayer1): _DenseLayer(
(norm1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 1,024 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 65,536 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 103,680 params
(denselayer2): _DenseLayer(
(norm1): BatchNorm2d(544, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 1,088 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(544, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 69,632 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 107,840 params
(denselayer3): _DenseLayer(
(norm1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 1,152 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(576, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 73,728 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 112,000 params
(denselayer4): _DenseLayer(
(norm1): BatchNorm2d(608, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 1,216 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(608, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 77,824 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 116,160 params
(denselayer5): _DenseLayer(
(norm1): BatchNorm2d(640, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 1,280 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(640, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 81,920 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 120,320 params
(denselayer6): _DenseLayer(
(norm1): BatchNorm2d(672, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 1,344 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(672, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 86,016 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 124,480 params
(denselayer7): _DenseLayer(
(norm1): BatchNorm2d(704, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 1,408 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(704, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 90,112 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 128,640 params
(denselayer8): _DenseLayer(
(norm1): BatchNorm2d(736, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 1,472 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(736, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 94,208 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 132,800 params
(denselayer9): _DenseLayer(
(norm1): BatchNorm2d(768, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 1,536 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(768, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 98,304 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 136,960 params
(denselayer10): _DenseLayer(
(norm1): BatchNorm2d(800, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 1,600 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(800, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 102,400 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 141,120 params
(denselayer11): _DenseLayer(
(norm1): BatchNorm2d(832, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 1,664 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(832, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 106,496 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 145,280 params
(denselayer12): _DenseLayer(
(norm1): BatchNorm2d(864, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 1,728 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(864, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 110,592 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 149,440 params
(denselayer13): _DenseLayer(
(norm1): BatchNorm2d(896, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 1,792 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(896, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 114,688 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 153,600 params
(denselayer14): _DenseLayer(
(norm1): BatchNorm2d(928, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 1,856 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(928, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 118,784 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 157,760 params
(denselayer15): _DenseLayer(
(norm1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 1,920 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(960, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 122,880 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 161,920 params
(denselayer16): _DenseLayer(
(norm1): BatchNorm2d(992, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 1,984 params
(relu1): ReLU(inplace=True), 0 params
(conv1): Conv2d(992, 128, kernel_size=(1, 1), stride=(1, 1), bias=False), 126,976 params
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 256 params
(relu2): ReLU(inplace=True), 0 params
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False), 36,864 params
), 166,080 params
), 2,158,080 params
(norm5): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True), 2,048 params
), 6,953,856 params
(classifier): Sequential(
(0): Linear(in_features=512, out_features=128, bias=True), 65,664 params
(1): ReLU(), 0 params
(2): Dropout(p=0.2, inplace=False), 0 params
(3): Linear(in_features=128, out_features=1, bias=True), 129 params
(4): Sigmoid(), 0 params
), 65,793 params
(avgpool): AdaptiveAvgPool2d(output_size=(1, 1)), 0 params
), 7,019,649 params
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
<ipython-input-59-6b3cd4462a8b> in <module>
23
24 model, criterion, optimizer = get_model()
---> 25 summary(model, torch.ones((1,3,IMAGE_SIZE,IMAGE_SIZE)).to(device), show_input=True, show_hierarchical=True)
/opt/conda/lib/python3.6/site-packages/modelsummary/modelsummary.py in summary(model, batch_size, show_input, show_hierarchical, *inputs)
68 # register hook
69 model.apply(register_hook)
---> 70 model(*inputs)
71
72 # remove these hooks
/opt/conda/lib/python3.6/site-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
530 result = self._slow_forward(*input, **kwargs)
531 else:
--> 532 result = self.forward(*input, **kwargs)
533 for hook in self._forward_hooks.values():
534 hook_result = hook(self, input, result)
/opt/conda/lib/python3.6/site-packages/torchvision/models/densenet.py in forward(self, x)
192
193 def forward(self, x):
--> 194 features = self.features(x)
195 out = F.relu(features, inplace=True)
196 out = F.adaptive_avg_pool2d(out, (1, 1))
/opt/conda/lib/python3.6/site-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
530 result = self._slow_forward(*input, **kwargs)
531 else:
--> 532 result = self.forward(*input, **kwargs)
533 for hook in self._forward_hooks.values():
534 hook_result = hook(self, input, result)
/opt/conda/lib/python3.6/site-packages/torch/nn/modules/container.py in forward(self, input)
98 def forward(self, input):
99 for module in self:
--> 100 input = module(input)
101 return input
102
/opt/conda/lib/python3.6/site-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
530 result = self._slow_forward(*input, **kwargs)
531 else:
--> 532 result = self.forward(*input, **kwargs)
533 for hook in self._forward_hooks.values():
534 hook_result = hook(self, input, result)
/opt/conda/lib/python3.6/site-packages/torchvision/models/densenet.py in forward(self, init_features)
109 features = [init_features]
110 for name, layer in self.items():
--> 111 new_features = layer(features)
112 features.append(new_features)
113 return torch.cat(features, 1)
/opt/conda/lib/python3.6/site-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
522 def __call__(self, *input, **kwargs):
523 for hook in self._forward_pre_hooks.values():
--> 524 result = hook(self, input)
525 if result is not None:
526 if not isinstance(result, tuple):
/opt/conda/lib/python3.6/site-packages/modelsummary/modelsummary.py in hook(module, input, output)
28
29 if len(input) != 0 :
---> 30 summary[m_key]["input_shape"] = list(input[0].size())
31 summary[m_key]["input_shape"][0] = batch_size
32 else:
AttributeError: 'list' object has no attribute 'size'
