What deeplearning networks does pretrained models belongs to?

Hi i am working in Deeplearning (Classification) for my project and i am using some pretrained network like vgg16 , vgg19 ,Alexnet for my project and i want to know on what deepLearning framework basis that these pretrained networks are working .

Thanks in advance

Answer 1

[Image Analyst]

Not sure about vgg (I haven't used them), but alexnet is a "convolutional neural network" used for classification (basically finding if the image has one of a predefined set of objects anywhere in the image - like "is there a dog, cat, or lizard anywhere in this image?").

[Venkatesh Kumar V]

Sir i want to know about framework Sir like TensorFlow, Keras,pytorch etc

[Image Analyst]

I think you're in the wrong forum. A survey by Gartner showed MATLAB tools to be better than those but if you still want those tools, look in a forum that deals with those tools.

https://www.mathworks.com/campaigns/offers/gartner-mq-2021-data-science-machine-learning-platforms.html?s_eid=psm_dl&source=15308

Answer 2

[yanqi liu]

yes，sir，may be load the pretrained model，and check its Layers，use image reshape to match inputLayer size，then get the classify result through model Layers parameter compute. if want to watch middle layers work，may be use activations or deepDreamImage to view them, such as

net = alexnet;
net.Layers

ans = 
  25×1 Layer array with layers:

     1   'data'     Image Input                   227×227×3 images with 'zerocenter' normalization
     2   'conv1'    Convolution                   96 11×11×3 convolutions with stride [4  4] and padding [0  0  0  0]
     3   'relu1'    ReLU                          ReLU
     4   'norm1'    Cross Channel Normalization   cross channel normalization with 5 channels per element
     5   'pool1'    Max Pooling                   3×3 max pooling with stride [2  2] and padding [0  0  0  0]
     6   'conv2'    Grouped Convolution           2 groups of 128 5×5×48 convolutions with stride [1  1] and padding [2  2  2  2]
     7   'relu2'    ReLU                          ReLU
     8   'norm2'    Cross Channel Normalization   cross channel normalization with 5 channels per element
     9   'pool2'    Max Pooling                   3×3 max pooling with stride [2  2] and padding [0  0  0  0]
    10   'conv3'    Convolution                   384 3×3×256 convolutions with stride [1  1] and padding [1  1  1  1]
    11   'relu3'    ReLU                          ReLU
    12   'conv4'    Grouped Convolution           2 groups of 192 3×3×192 convolutions with stride [1  1] and padding [1  1  1  1]
    13   'relu4'    ReLU                          ReLU
    14   'conv5'    Grouped Convolution           2 groups of 128 3×3×192 convolutions with stride [1  1] and padding [1  1  1  1]
    15   'relu5'    ReLU                          ReLU
    16   'pool5'    Max Pooling                   3×3 max pooling with stride [2  2] and padding [0  0  0  0]
    17   'fc6'      Fully Connected               4096 fully connected layer
    18   'relu6'    ReLU                          ReLU
    19   'drop6'    Dropout                       50% dropout
    20   'fc7'      Fully Connected               4096 fully connected layer
    21   'relu7'    ReLU                          ReLU
    22   'drop7'    Dropout                       50% dropout
    23   'fc8'      Fully Connected               1000 fully connected layer
    24   'prob'     Softmax                       softmax
    25   'output'   Classification Output         crossentropyex with 'tench' and 999 other classes

layer = 'conv1';
channels = 1:25;

I = deepDreamImage(net,layer,channels, ...
    'PyramidLevels',1, ...
    'Verbose',0);

figure
for i = 1:25
    subplot(5,5,i)
    imshow(I(:,:,:,i))
end