search

lindawangg / COVID-Net

COVID-Net Open Source Initiative
Other
1.15k stars 480 forks source link

Can't reconcile layer dimensions in chart from COVID_Netv2.pdf #30

Closed Justus-M closed 4 years ago

Justus-M commented 4 years ago

Hi, First of all thanks for sharing your work.

  1. When will you release the training script?
  2. I can't seem to reconcile the layer dimensions in the PDF. The first layer gives the dimensions of the input images in parentheses, so I assume the numbers in parentheses are the dimensions of what is passed to the next layer. If so, how does a 7x7 convolutional layer output 112x112x64 from an input of 224x224x3? Assuming step size and padding size are integers, this doesn't seem to work with the formula for calculating the output size of convolutions unless you have unreasonably huge padding.

For the conv1x1 layers the dimension gets cut in half, suggesting the step size is 2. However with a 1x1 filter this means you're dropping half of the pixels. Is this correct?

Furthermore, the first flatten layer is said to have a flattened dimension of 100352 - but that's what you'd get from just PEPX 4.3. However you also have PEPX 4.2, PEPX 4.1, and the last conv1x1 on the right all feeding into the flattened layer, which each have 100352 elements. so are these 4x100352 all flattened together, feeding a vector of 401408 elements into the first FC layer (as I would expect since they all come from the same input image), or are you treating them separately?

  1. Could you please specify the PEPX layer dimensions?
Justus-M commented 4 years ago

Perhaps pooling could explain the dimension mismatch? But there is no mention of pooling anywhere