-
Notifications
You must be signed in to change notification settings - Fork 0
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Description of architecture #6
Comments
ENCODER Input: 256x256x3 Layer 1: Convolution with 32 filters, kernelsize 3, strides of 2, activation fuction Relu Layer 2: Convolution with 64 filters, kernelsize 3, strides of 2, activation fuction Relu Layer 3: Convolution with 64 filters, kernelsize 3, strides of 2, activation fuction Relu Layer 4: Flatten Layer 5: Dense to 256 with no activation function Die Hälfte (128) von Layer5 wird als Mittelwert und die andere Hälfte als Standardabweichung genommen und damit aus der Normalverteilung 128 Werte gesampled: DECODER Input: 128 Layer1: Dense to 32^3 with activation function Relu Layer2: Reshape to 32x32x32 Layer3: Convolution Transposed with 32 filters, kernelsize 3, strides of 2, activation function Relu Layer4: Convolution Transposed with 32 filters, kernelsize 3, strides of 2, activation function Relu Layer5: Convolution Transposed with 32 filters, kernelsize 3, strides of 2, activation function Relu Layer6: Convolution Transposed with 3 filters, kernelsize 3, strides of 1, no activation function |
Zum vergleich ist hier die Architektur von dem CVAE für MNIST der gut nachstellbar funktioniert ENCODER Input: 28x28x1 Layer 1: Convolution with 32 filters, kernelsize 3, strides of 2, activation fuction Relu Layer 2: Convolution with 64 filters, kernelsize 3, strides of 2, activation fuction Relu Layer 3: Flatten Layer 4: Dense to 50 with no activation function Die Hälfte (25) von Layer4 wird als Mittelwert und die andere Hälfte als Standardabweichung genommen und damit aus der Normalverteilung 128 Werte gesampled: DECODER Input: 25 Layer1: Dense to 7732 with activation function Relu Layer2: Reshape to 7x7x32 Layer3: Convolution Transposed with 64 filters, kernelsize 3, strides of 2, activation function Relu Layer4: Convolution Transposed with 32 filters, kernelsize 3, strides of 2, activation function Relu Layer5: Convolution Transposed with 1 filter, kernelsize 3, strides of 1, no activation function |
I need much more information about the architecture. I think it can be meaningful, f we have always a short table which contains the successively applied layer (convolutional (and strides), (un)pooling layers, ReLU functions, skip connections as well as input size of images and resulting feature maps). Can you create a document for the latest architecture, which describe this sequence. With a current description we may discuss with matthias a little bit better.
The text was updated successfully, but these errors were encountered: