“Proportionate Selection” The smaller the fitness, the better, but the smaller the probability of selection.

Evolving-CNNs-using-GA/src/utilities.py", line 32, in save_network
pickle.dump(network, object_file)
TypeError: can't pickle weakref objects
Excuse me, how to solve this problem ?

Model: "sequential"

Layer (type) Output Shape Param #

conv2d (Conv2D) (None, 32, 32, 32) 896

conv2d_1 (Conv2D) (None, 30, 30, 32) 9248

max_pooling2d (MaxPooling2D) (None, 15, 15, 32) 0

flatten (Flatten) (None, 7200) 0

dense (Dense) (None, 128) 921728

dense_1 (Dense) (None, 10) 1290

Total params: 933,162
Trainable params: 933,162
Non-trainable params: 0

None
FITNESS: 1.118133783340454
Traceback (most recent call last):
File "main.py", line 216, in
main()
File "main.py", line 181, in main
optCNN = genetic_algorithm(num_population, num_generation, num_offspring, dataset)
File "main.py", line 76, in genetic_algorithm
population = initialize_population(num_population, dataset)
File "main.py", line 15, in initialize_population
daddy = compute_parent(dataset) # load parent from input
File "/home/guohy/ECNN/Evolving-CNNs-using-GA/src/inout.py", line 62, in compute_parent
daddy.train_and_evaluate(model, dataset)
File "/home/guohy/ECNN/Evolving-CNNs-using-GA/src/network.py", line 52, in train_and_evaluate
save_network(self) # save topology, model and fitness
File "/home/guohy/ECNN/Evolving-CNNs-using-GA/src/utilities.py", line 31, in save_network
pickle.dump(network, object_file)
TypeError: can't pickle _thread.RLock objects

Could you tell me how to solve the problem?Thank you very much.

Excuse me, how is the VGG-2 model mentioned in the article implemented? I tried to remove the comment symbols in the inout.py file, but the result is still the VGG-1 model. What parameters do I need to adjust?