Formation of the neural network architecture of the model and downloading its weights to obtain deep features (video modality)
_b5.video_model_deep_fe_
- Neural network model tf.keras.Model for obtaining deep features
Import required packages
[2]:
from oceanai.modules.lab.build import Run
Build
[3]:
_b5 = Run(
lang = 'en', # Inference language
color_simple = '#333', # Plain text color (hexadecimal code)
color_info = '#1776D2', # The color of the text containing the information (hexadecimal code)
color_err = '#FF0000', # Error text color (hexadecimal code)
color_true = '#008001', # Text color containing positive information (hexadecimal code)
bold_text = True, # Bold text
num_to_df_display = 30, # Number of rows to display in tables
text_runtime = 'Runtime', # Runtime text
metadata = True # Displaying information about library
)
[2023-12-10 17:08:31] OCEANAI - personality traits: Authors: Elena Ryumina [ryumina_ev@mail.ru] Dmitry Ryumin [dl_03.03.1991@mail.ru] Alexey Karpov [karpov@iias.spb.su] Maintainers: Elena Ryumina [ryumina_ev@mail.ru] Dmitry Ryumin [dl_03.03.1991@mail.ru] Version: 1.0.0a5 License: BSD License
Formation of the neural network architecture of the model (FI V2
)
[4]:
res_load_video_model_deep_fe = _b5.load_video_model_deep_fe(
show_summary = False, # Displaying the formed neural network architecture of the model
out = True, # Display
runtime = True, # Runtime count
run = True # Run blocking
)
[2023-12-10 17:08:31] Formation of neural network architecture for obtaining deep features (video modality) …
— Runtime: 1.118 sec. —
Downloading the weights of the neural network model
[5]:
# Core settings
_b5.path_to_save_ = './models' # Directory to save the file
_b5.chunk_size_ = 2000000 # File download size from network in 1 step
url = _b5.weights_for_big5_['video']['fi']['fe']['sberdisk']
res_load_video_model_weights_deep_fe = _b5.load_video_model_weights_deep_fe(
url = url, # Full path to the file with weights of the neural network model
force_reload = True, # Forced download of a file with weights of a neural network model from the network
out = True, # Display
runtime = True, # Runtime count
run = True # Run blocking
)
[2023-12-10 17:08:32] Downloading weights of a neural network model to obtain deep features (video modality) …
[2023-12-10 17:08:36] File download “weights_2022-11-01_12-27-07.h5” (100.0%) …
— Runtime: 4.042 sec. —
Displaying the formed neural network architecture of the model
[6]:
_b5.video_model_deep_fe_.summary()
Model: "model_1"
__________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
==================================================================================================
input_1 (InputLayer) [(None, 224, 224, 3 0 []
)]
conv1/7x7_s2 (Conv2D) (None, 112, 112, 64 9408 ['input_1[0][0]']
)
conv1/7x7_s2/bn (BatchNormaliz (None, 112, 112, 64 256 ['conv1/7x7_s2[0][0]']
ation) )
activation (Activation) (None, 112, 112, 64 0 ['conv1/7x7_s2/bn[0][0]']
)
max_pooling2d (MaxPooling2D) (None, 55, 55, 64) 0 ['activation[0][0]']
conv2_1_1x1_reduce (Conv2D) (None, 55, 55, 64) 4096 ['max_pooling2d[0][0]']
conv2_1_1x1_reduce/bn (BatchNo (None, 55, 55, 64) 256 ['conv2_1_1x1_reduce[0][0]']
rmalization)
activation_1 (Activation) (None, 55, 55, 64) 0 ['conv2_1_1x1_reduce/bn[0][0]']
conv2_1_3x3 (Conv2D) (None, 55, 55, 64) 36864 ['activation_1[0][0]']
conv2_1_3x3/bn (BatchNormaliza (None, 55, 55, 64) 256 ['conv2_1_3x3[0][0]']
tion)
activation_2 (Activation) (None, 55, 55, 64) 0 ['conv2_1_3x3/bn[0][0]']
conv2_1_1x1_increase (Conv2D) (None, 55, 55, 256) 16384 ['activation_2[0][0]']
conv2_1_1x1_proj (Conv2D) (None, 55, 55, 256) 16384 ['max_pooling2d[0][0]']
conv2_1_1x1_increase/bn (Batch (None, 55, 55, 256) 1024 ['conv2_1_1x1_increase[0][0]']
Normalization)
conv2_1_1x1_proj/bn (BatchNorm (None, 55, 55, 256) 1024 ['conv2_1_1x1_proj[0][0]']
alization)
add (Add) (None, 55, 55, 256) 0 ['conv2_1_1x1_increase/bn[0][0]',
'conv2_1_1x1_proj/bn[0][0]']
activation_3 (Activation) (None, 55, 55, 256) 0 ['add[0][0]']
conv2_2_1x1_reduce (Conv2D) (None, 55, 55, 64) 16384 ['activation_3[0][0]']
conv2_2_1x1_reduce/bn (BatchNo (None, 55, 55, 64) 256 ['conv2_2_1x1_reduce[0][0]']
rmalization)
activation_4 (Activation) (None, 55, 55, 64) 0 ['conv2_2_1x1_reduce/bn[0][0]']
conv2_2_3x3 (Conv2D) (None, 55, 55, 64) 36864 ['activation_4[0][0]']
conv2_2_3x3/bn (BatchNormaliza (None, 55, 55, 64) 256 ['conv2_2_3x3[0][0]']
tion)
activation_5 (Activation) (None, 55, 55, 64) 0 ['conv2_2_3x3/bn[0][0]']
conv2_2_1x1_increase (Conv2D) (None, 55, 55, 256) 16384 ['activation_5[0][0]']
conv2_2_1x1_increase/bn (Batch (None, 55, 55, 256) 1024 ['conv2_2_1x1_increase[0][0]']
Normalization)
add_1 (Add) (None, 55, 55, 256) 0 ['conv2_2_1x1_increase/bn[0][0]',
'activation_3[0][0]']
activation_6 (Activation) (None, 55, 55, 256) 0 ['add_1[0][0]']
conv2_3_1x1_reduce (Conv2D) (None, 55, 55, 64) 16384 ['activation_6[0][0]']
conv2_3_1x1_reduce/bn (BatchNo (None, 55, 55, 64) 256 ['conv2_3_1x1_reduce[0][0]']
rmalization)
activation_7 (Activation) (None, 55, 55, 64) 0 ['conv2_3_1x1_reduce/bn[0][0]']
conv2_3_3x3 (Conv2D) (None, 55, 55, 64) 36864 ['activation_7[0][0]']
conv2_3_3x3/bn (BatchNormaliza (None, 55, 55, 64) 256 ['conv2_3_3x3[0][0]']
tion)
activation_8 (Activation) (None, 55, 55, 64) 0 ['conv2_3_3x3/bn[0][0]']
conv2_3_1x1_increase (Conv2D) (None, 55, 55, 256) 16384 ['activation_8[0][0]']
conv2_3_1x1_increase/bn (Batch (None, 55, 55, 256) 1024 ['conv2_3_1x1_increase[0][0]']
Normalization)
add_2 (Add) (None, 55, 55, 256) 0 ['conv2_3_1x1_increase/bn[0][0]',
'activation_6[0][0]']
activation_9 (Activation) (None, 55, 55, 256) 0 ['add_2[0][0]']
conv3_1_1x1_reduce (Conv2D) (None, 28, 28, 128) 32768 ['activation_9[0][0]']
conv3_1_1x1_reduce/bn (BatchNo (None, 28, 28, 128) 512 ['conv3_1_1x1_reduce[0][0]']
rmalization)
activation_10 (Activation) (None, 28, 28, 128) 0 ['conv3_1_1x1_reduce/bn[0][0]']
conv3_1_3x3 (Conv2D) (None, 28, 28, 128) 147456 ['activation_10[0][0]']
conv3_1_3x3/bn (BatchNormaliza (None, 28, 28, 128) 512 ['conv3_1_3x3[0][0]']
tion)
activation_11 (Activation) (None, 28, 28, 128) 0 ['conv3_1_3x3/bn[0][0]']
conv3_1_1x1_increase (Conv2D) (None, 28, 28, 512) 65536 ['activation_11[0][0]']
conv3_1_1x1_proj (Conv2D) (None, 28, 28, 512) 131072 ['activation_9[0][0]']
conv3_1_1x1_increase/bn (Batch (None, 28, 28, 512) 2048 ['conv3_1_1x1_increase[0][0]']
Normalization)
conv3_1_1x1_proj/bn (BatchNorm (None, 28, 28, 512) 2048 ['conv3_1_1x1_proj[0][0]']
alization)
add_3 (Add) (None, 28, 28, 512) 0 ['conv3_1_1x1_increase/bn[0][0]',
'conv3_1_1x1_proj/bn[0][0]']
activation_12 (Activation) (None, 28, 28, 512) 0 ['add_3[0][0]']
conv3_2_1x1_reduce (Conv2D) (None, 28, 28, 128) 65536 ['activation_12[0][0]']
conv3_2_1x1_reduce/bn (BatchNo (None, 28, 28, 128) 512 ['conv3_2_1x1_reduce[0][0]']
rmalization)
activation_13 (Activation) (None, 28, 28, 128) 0 ['conv3_2_1x1_reduce/bn[0][0]']
conv3_2_3x3 (Conv2D) (None, 28, 28, 128) 147456 ['activation_13[0][0]']
conv3_2_3x3/bn (BatchNormaliza (None, 28, 28, 128) 512 ['conv3_2_3x3[0][0]']
tion)
activation_14 (Activation) (None, 28, 28, 128) 0 ['conv3_2_3x3/bn[0][0]']
conv3_2_1x1_increase (Conv2D) (None, 28, 28, 512) 65536 ['activation_14[0][0]']
conv3_2_1x1_increase/bn (Batch (None, 28, 28, 512) 2048 ['conv3_2_1x1_increase[0][0]']
Normalization)
add_4 (Add) (None, 28, 28, 512) 0 ['conv3_2_1x1_increase/bn[0][0]',
'activation_12[0][0]']
activation_15 (Activation) (None, 28, 28, 512) 0 ['add_4[0][0]']
conv3_3_1x1_reduce (Conv2D) (None, 28, 28, 128) 65536 ['activation_15[0][0]']
conv3_3_1x1_reduce/bn (BatchNo (None, 28, 28, 128) 512 ['conv3_3_1x1_reduce[0][0]']
rmalization)
activation_16 (Activation) (None, 28, 28, 128) 0 ['conv3_3_1x1_reduce/bn[0][0]']
conv3_3_3x3 (Conv2D) (None, 28, 28, 128) 147456 ['activation_16[0][0]']
conv3_3_3x3/bn (BatchNormaliza (None, 28, 28, 128) 512 ['conv3_3_3x3[0][0]']
tion)
activation_17 (Activation) (None, 28, 28, 128) 0 ['conv3_3_3x3/bn[0][0]']
conv3_3_1x1_increase (Conv2D) (None, 28, 28, 512) 65536 ['activation_17[0][0]']
conv3_3_1x1_increase/bn (Batch (None, 28, 28, 512) 2048 ['conv3_3_1x1_increase[0][0]']
Normalization)
add_5 (Add) (None, 28, 28, 512) 0 ['conv3_3_1x1_increase/bn[0][0]',
'activation_15[0][0]']
activation_18 (Activation) (None, 28, 28, 512) 0 ['add_5[0][0]']
conv3_4_1x1_reduce (Conv2D) (None, 28, 28, 128) 65536 ['activation_18[0][0]']
conv3_4_1x1_reduce/bn (BatchNo (None, 28, 28, 128) 512 ['conv3_4_1x1_reduce[0][0]']
rmalization)
activation_19 (Activation) (None, 28, 28, 128) 0 ['conv3_4_1x1_reduce/bn[0][0]']
conv3_4_3x3 (Conv2D) (None, 28, 28, 128) 147456 ['activation_19[0][0]']
conv3_4_3x3/bn (BatchNormaliza (None, 28, 28, 128) 512 ['conv3_4_3x3[0][0]']
tion)
activation_20 (Activation) (None, 28, 28, 128) 0 ['conv3_4_3x3/bn[0][0]']
conv3_4_1x1_increase (Conv2D) (None, 28, 28, 512) 65536 ['activation_20[0][0]']
conv3_4_1x1_increase/bn (Batch (None, 28, 28, 512) 2048 ['conv3_4_1x1_increase[0][0]']
Normalization)
add_6 (Add) (None, 28, 28, 512) 0 ['conv3_4_1x1_increase/bn[0][0]',
'activation_18[0][0]']
activation_21 (Activation) (None, 28, 28, 512) 0 ['add_6[0][0]']
conv4_1_1x1_reduce (Conv2D) (None, 14, 14, 256) 131072 ['activation_21[0][0]']
conv4_1_1x1_reduce/bn (BatchNo (None, 14, 14, 256) 1024 ['conv4_1_1x1_reduce[0][0]']
rmalization)
activation_22 (Activation) (None, 14, 14, 256) 0 ['conv4_1_1x1_reduce/bn[0][0]']
conv4_1_3x3 (Conv2D) (None, 14, 14, 256) 589824 ['activation_22[0][0]']
conv4_1_3x3/bn (BatchNormaliza (None, 14, 14, 256) 1024 ['conv4_1_3x3[0][0]']
tion)
activation_23 (Activation) (None, 14, 14, 256) 0 ['conv4_1_3x3/bn[0][0]']
conv4_1_1x1_increase (Conv2D) (None, 14, 14, 1024 262144 ['activation_23[0][0]']
)
conv4_1_1x1_proj (Conv2D) (None, 14, 14, 1024 524288 ['activation_21[0][0]']
)
conv4_1_1x1_increase/bn (Batch (None, 14, 14, 1024 4096 ['conv4_1_1x1_increase[0][0]']
Normalization) )
conv4_1_1x1_proj/bn (BatchNorm (None, 14, 14, 1024 4096 ['conv4_1_1x1_proj[0][0]']
alization) )
add_7 (Add) (None, 14, 14, 1024 0 ['conv4_1_1x1_increase/bn[0][0]',
) 'conv4_1_1x1_proj/bn[0][0]']
activation_24 (Activation) (None, 14, 14, 1024 0 ['add_7[0][0]']
)
conv4_2_1x1_reduce (Conv2D) (None, 14, 14, 256) 262144 ['activation_24[0][0]']
conv4_2_1x1_reduce/bn (BatchNo (None, 14, 14, 256) 1024 ['conv4_2_1x1_reduce[0][0]']
rmalization)
activation_25 (Activation) (None, 14, 14, 256) 0 ['conv4_2_1x1_reduce/bn[0][0]']
conv4_2_3x3 (Conv2D) (None, 14, 14, 256) 589824 ['activation_25[0][0]']
conv4_2_3x3/bn (BatchNormaliza (None, 14, 14, 256) 1024 ['conv4_2_3x3[0][0]']
tion)
activation_26 (Activation) (None, 14, 14, 256) 0 ['conv4_2_3x3/bn[0][0]']
conv4_2_1x1_increase (Conv2D) (None, 14, 14, 1024 262144 ['activation_26[0][0]']
)
conv4_2_1x1_increase/bn (Batch (None, 14, 14, 1024 4096 ['conv4_2_1x1_increase[0][0]']
Normalization) )
add_8 (Add) (None, 14, 14, 1024 0 ['conv4_2_1x1_increase/bn[0][0]',
) 'activation_24[0][0]']
activation_27 (Activation) (None, 14, 14, 1024 0 ['add_8[0][0]']
)
conv4_3_1x1_reduce (Conv2D) (None, 14, 14, 256) 262144 ['activation_27[0][0]']
conv4_3_1x1_reduce/bn (BatchNo (None, 14, 14, 256) 1024 ['conv4_3_1x1_reduce[0][0]']
rmalization)
activation_28 (Activation) (None, 14, 14, 256) 0 ['conv4_3_1x1_reduce/bn[0][0]']
conv4_3_3x3 (Conv2D) (None, 14, 14, 256) 589824 ['activation_28[0][0]']
conv4_3_3x3/bn (BatchNormaliza (None, 14, 14, 256) 1024 ['conv4_3_3x3[0][0]']
tion)
activation_29 (Activation) (None, 14, 14, 256) 0 ['conv4_3_3x3/bn[0][0]']
conv4_3_1x1_increase (Conv2D) (None, 14, 14, 1024 262144 ['activation_29[0][0]']
)
conv4_3_1x1_increase/bn (Batch (None, 14, 14, 1024 4096 ['conv4_3_1x1_increase[0][0]']
Normalization) )
add_9 (Add) (None, 14, 14, 1024 0 ['conv4_3_1x1_increase/bn[0][0]',
) 'activation_27[0][0]']
activation_30 (Activation) (None, 14, 14, 1024 0 ['add_9[0][0]']
)
conv4_4_1x1_reduce (Conv2D) (None, 14, 14, 256) 262144 ['activation_30[0][0]']
conv4_4_1x1_reduce/bn (BatchNo (None, 14, 14, 256) 1024 ['conv4_4_1x1_reduce[0][0]']
rmalization)
activation_31 (Activation) (None, 14, 14, 256) 0 ['conv4_4_1x1_reduce/bn[0][0]']
conv4_4_3x3 (Conv2D) (None, 14, 14, 256) 589824 ['activation_31[0][0]']
conv4_4_3x3/bn (BatchNormaliza (None, 14, 14, 256) 1024 ['conv4_4_3x3[0][0]']
tion)
activation_32 (Activation) (None, 14, 14, 256) 0 ['conv4_4_3x3/bn[0][0]']
conv4_4_1x1_increase (Conv2D) (None, 14, 14, 1024 262144 ['activation_32[0][0]']
)
conv4_4_1x1_increase/bn (Batch (None, 14, 14, 1024 4096 ['conv4_4_1x1_increase[0][0]']
Normalization) )
add_10 (Add) (None, 14, 14, 1024 0 ['conv4_4_1x1_increase/bn[0][0]',
) 'activation_30[0][0]']
activation_33 (Activation) (None, 14, 14, 1024 0 ['add_10[0][0]']
)
conv4_5_1x1_reduce (Conv2D) (None, 14, 14, 256) 262144 ['activation_33[0][0]']
conv4_5_1x1_reduce/bn (BatchNo (None, 14, 14, 256) 1024 ['conv4_5_1x1_reduce[0][0]']
rmalization)
activation_34 (Activation) (None, 14, 14, 256) 0 ['conv4_5_1x1_reduce/bn[0][0]']
conv4_5_3x3 (Conv2D) (None, 14, 14, 256) 589824 ['activation_34[0][0]']
conv4_5_3x3/bn (BatchNormaliza (None, 14, 14, 256) 1024 ['conv4_5_3x3[0][0]']
tion)
activation_35 (Activation) (None, 14, 14, 256) 0 ['conv4_5_3x3/bn[0][0]']
conv4_5_1x1_increase (Conv2D) (None, 14, 14, 1024 262144 ['activation_35[0][0]']
)
conv4_5_1x1_increase/bn (Batch (None, 14, 14, 1024 4096 ['conv4_5_1x1_increase[0][0]']
Normalization) )
add_11 (Add) (None, 14, 14, 1024 0 ['conv4_5_1x1_increase/bn[0][0]',
) 'activation_33[0][0]']
activation_36 (Activation) (None, 14, 14, 1024 0 ['add_11[0][0]']
)
conv4_6_1x1_reduce (Conv2D) (None, 14, 14, 256) 262144 ['activation_36[0][0]']
conv4_6_1x1_reduce/bn (BatchNo (None, 14, 14, 256) 1024 ['conv4_6_1x1_reduce[0][0]']
rmalization)
activation_37 (Activation) (None, 14, 14, 256) 0 ['conv4_6_1x1_reduce/bn[0][0]']
conv4_6_3x3 (Conv2D) (None, 14, 14, 256) 589824 ['activation_37[0][0]']
conv4_6_3x3/bn (BatchNormaliza (None, 14, 14, 256) 1024 ['conv4_6_3x3[0][0]']
tion)
activation_38 (Activation) (None, 14, 14, 256) 0 ['conv4_6_3x3/bn[0][0]']
conv4_6_1x1_increase (Conv2D) (None, 14, 14, 1024 262144 ['activation_38[0][0]']
)
conv4_6_1x1_increase/bn (Batch (None, 14, 14, 1024 4096 ['conv4_6_1x1_increase[0][0]']
Normalization) )
add_12 (Add) (None, 14, 14, 1024 0 ['conv4_6_1x1_increase/bn[0][0]',
) 'activation_36[0][0]']
activation_39 (Activation) (None, 14, 14, 1024 0 ['add_12[0][0]']
)
conv5_1_1x1_reduce (Conv2D) (None, 7, 7, 512) 524288 ['activation_39[0][0]']
conv5_1_1x1_reduce/bn (BatchNo (None, 7, 7, 512) 2048 ['conv5_1_1x1_reduce[0][0]']
rmalization)
activation_40 (Activation) (None, 7, 7, 512) 0 ['conv5_1_1x1_reduce/bn[0][0]']
conv5_1_3x3 (Conv2D) (None, 7, 7, 512) 2359296 ['activation_40[0][0]']
conv5_1_3x3/bn (BatchNormaliza (None, 7, 7, 512) 2048 ['conv5_1_3x3[0][0]']
tion)
activation_41 (Activation) (None, 7, 7, 512) 0 ['conv5_1_3x3/bn[0][0]']
conv5_1_1x1_increase (Conv2D) (None, 7, 7, 2048) 1048576 ['activation_41[0][0]']
conv5_1_1x1_proj (Conv2D) (None, 7, 7, 2048) 2097152 ['activation_39[0][0]']
conv5_1_1x1_increase/bn (Batch (None, 7, 7, 2048) 8192 ['conv5_1_1x1_increase[0][0]']
Normalization)
conv5_1_1x1_proj/bn (BatchNorm (None, 7, 7, 2048) 8192 ['conv5_1_1x1_proj[0][0]']
alization)
add_13 (Add) (None, 7, 7, 2048) 0 ['conv5_1_1x1_increase/bn[0][0]',
'conv5_1_1x1_proj/bn[0][0]']
activation_42 (Activation) (None, 7, 7, 2048) 0 ['add_13[0][0]']
conv5_2_1x1_reduce (Conv2D) (None, 7, 7, 512) 1048576 ['activation_42[0][0]']
conv5_2_1x1_reduce/bn (BatchNo (None, 7, 7, 512) 2048 ['conv5_2_1x1_reduce[0][0]']
rmalization)
activation_43 (Activation) (None, 7, 7, 512) 0 ['conv5_2_1x1_reduce/bn[0][0]']
conv5_2_3x3 (Conv2D) (None, 7, 7, 512) 2359296 ['activation_43[0][0]']
conv5_2_3x3/bn (BatchNormaliza (None, 7, 7, 512) 2048 ['conv5_2_3x3[0][0]']
tion)
activation_44 (Activation) (None, 7, 7, 512) 0 ['conv5_2_3x3/bn[0][0]']
conv5_2_1x1_increase (Conv2D) (None, 7, 7, 2048) 1048576 ['activation_44[0][0]']
conv5_2_1x1_increase/bn (Batch (None, 7, 7, 2048) 8192 ['conv5_2_1x1_increase[0][0]']
Normalization)
add_14 (Add) (None, 7, 7, 2048) 0 ['conv5_2_1x1_increase/bn[0][0]',
'activation_42[0][0]']
activation_45 (Activation) (None, 7, 7, 2048) 0 ['add_14[0][0]']
conv5_3_1x1_reduce (Conv2D) (None, 7, 7, 512) 1048576 ['activation_45[0][0]']
conv5_3_1x1_reduce/bn (BatchNo (None, 7, 7, 512) 2048 ['conv5_3_1x1_reduce[0][0]']
rmalization)
activation_46 (Activation) (None, 7, 7, 512) 0 ['conv5_3_1x1_reduce/bn[0][0]']
conv5_3_3x3 (Conv2D) (None, 7, 7, 512) 2359296 ['activation_46[0][0]']
conv5_3_3x3/bn (BatchNormaliza (None, 7, 7, 512) 2048 ['conv5_3_3x3[0][0]']
tion)
activation_47 (Activation) (None, 7, 7, 512) 0 ['conv5_3_3x3/bn[0][0]']
conv5_3_1x1_increase (Conv2D) (None, 7, 7, 2048) 1048576 ['activation_47[0][0]']
conv5_3_1x1_increase/bn (Batch (None, 7, 7, 2048) 8192 ['conv5_3_1x1_increase[0][0]']
Normalization)
add_15 (Add) (None, 7, 7, 2048) 0 ['conv5_3_1x1_increase/bn[0][0]',
'activation_45[0][0]']
activation_48 (Activation) (None, 7, 7, 2048) 0 ['add_15[0][0]']
avg_pool (AveragePooling2D) (None, 1, 1, 2048) 0 ['activation_48[0][0]']
global_average_pooling2d (Glob (None, 2048) 0 ['avg_pool[0][0]']
alAveragePooling2D)
gaussian_noise (GaussianNoise) (None, 2048) 0 ['global_average_pooling2d[0][0]'
]
dense_x (Dense) (None, 512) 1049088 ['gaussian_noise[0][0]']
==================================================================================================
Total params: 24,610,240
Trainable params: 24,557,120
Non-trainable params: 53,120
__________________________________________________________________________________________________