python - How to generate a model summary or plot the model architecture in Tensorflow object detection models?

Question

Is it possible to view the model summary or plot the tensorflow object detection models available in Tensorflow object detection git repository. For example view the model summary for Faster R-CNN models?

question from:https://stackoverflow.com/questions/66063808/how-to-generate-a-model-summary-or-plot-the-model-architecture-in-tensorflow-obj

Answer 1

Model summary can be viewed by using model.summary() form Tensorflow. See the sample code.

# Create the base model from the pre-trained model MobileNet V2
IMG_SHAPE = IMG_SIZE + (3,)
base_model = tf.keras.applications.MobileNetV2(input_shape=IMG_SHAPE,
                                               include_top=False,
                                               weights='imagenet')

# Let's take a look at the base model architecture
base_model.summary()

#output

Model: "mobilenetv2_1.00_160"
__________________________________________________________________________________________________
Layer (type)                    Output Shape         Param #     Connected to                     
==================================================================================================
input_1 (InputLayer)            [(None, 160, 160, 3) 0                                            
__________________________________________________________________________________________________
Conv1 (Conv2D)                  (None, 80, 80, 32)   864         input_1[0][0]                    
__________________________________________________________________________________________________
bn_Conv1 (BatchNormalization)   (None, 80, 80, 32)   128         Conv1[0][0]                      
__________________________________________________________________________________________________
Conv1_relu (ReLU)               (None, 80, 80, 32)   0           bn_Conv1[0][0]                   
__________________________________________________________________________________________________
expanded_conv_depthwise (Depthw (None, 80, 80, 32)   288         Conv1_relu[0][0]                 
__________________________________________________________________________________________________