Formation of the neural network architecture of the model and downloading its weights to obtain features / scores based on hand-crafted features (text modality)


  • _b5.text_model_hc_ - Neural network model tf.keras.Model for obtaining features / scores by hand-crafted 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 17:11:13] 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_text_model_hc_fi = _b5.load_text_model_hc(
    corpus = "fi", # Corpus selection for models trained on First Impressions V2 'fi' and models trained on for MuPTA 'mupta'
    show_summary = False, # Displaying the formed neural network architecture of the model
    out = True, # Display
    runtime = True, # Runtime count
    run = True # Run blockin
)

[2023-12-10 17:11:13] Formation of the neural network architecture of the model for obtaining scores by hand-crafted features (text modality) …

— Runtime: 1.886 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_['text']['fi']['hc']['sberdisk']

res_load_text_model_weights_hc_fi = _b5.load_text_model_weights_hc(
    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 16:54:00] Downloading the weights of a neural network model to obtain hand-crafted features (text modality) …

[2023-12-10 16:54:01] File download “weights_2023-07-15_10-52-15.h5” 100.0% …

— Runtime: 0.311 sec. —

Displaying the formed neural network architecture of the model

[6]:
_b5.text_model_hc_.summary()
Model: "model"
__________________________________________________________________________________________________
 Layer (type)                   Output Shape         Param #     Connected to
==================================================================================================
 model_hc/input (InputLayer)    [(None, 89, 64)]     0           []

 model_hc/bilstm_1 (Bidirection  (None, 89, 64)      24832       ['model_hc/input[0][0]']
 al)

 model_hc/dence_2 (Dense)       (None, 89, 64)       4160        ['model_hc/input[0][0]']

 model_hc/attention (Attention)  (None, 89, 64)      0           ['model_hc/bilstm_1[0][0]',
                                                                  'model_hc/bilstm_1[0][0]']

 model_hc/bilstm_2 (Bidirection  (None, 89, 64)      24832       ['model_hc/dence_2[0][0]']
 al)

 add (Add)                      (None, 89, 64)       0           ['model_hc/bilstm_1[0][0]',
                                                                  'model_hc/attention[0][0]',
                                                                  'model_hc/bilstm_2[0][0]']

 model_hc/add (Addition)        (None, 128)          0           ['add[0][0]']

 dense (Dense)                  (None, 5)            645         ['model_hc/add[0][0]']

==================================================================================================
Total params: 54,469
Trainable params: 54,469
Non-trainable params: 0
__________________________________________________________________________________________________

Formation of the neural network architecture of the model (MuPTA)

[7]:
res_load_text_model_hc_mupta = _b5.load_text_model_hc(
    corpus = "mupta", # Corpus selection for models trained on First Impressions V2 'fi' and models trained on for MuPTA 'mupta'
    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 16:54:06] Formation of the neural network architecture of the model for obtaining scores by hand-crafted features (text modality) …

— Runtime: 0.577 sec. —

Downloading the weights of the neural network model

[8]:
# 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_['text']['mupta']['hc']['sberdisk']

res_load_text_model_weights_hc_mupta = _b5.load_text_model_weights_hc(
    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 16:54:19] Downloading the weights of a neural network model to obtain hand-crafted features (text modality) …

[2023-12-10 16:54:19] File download “weights_2023-07-15_10-53-38.h5” 100.0% …

— Runtime: 0.264 sec. —

Displaying the formed neural network architecture of the model

[9]:
_b5.text_model_hc_.summary()
Model: "model_1"
__________________________________________________________________________________________________
 Layer (type)                   Output Shape         Param #     Connected to
==================================================================================================
 model_hc/input (InputLayer)    [(None, 365, 64)]    0           []

 model_hc/bilstm_1 (Bidirection  (None, 365, 64)     24832       ['model_hc/input[0][0]']
 al)

 model_hc/dence_2 (Dense)       (None, 365, 64)      4160        ['model_hc/input[0][0]']

 model_hc/attention (Attention)  (None, 365, 64)     0           ['model_hc/bilstm_1[0][0]',
                                                                  'model_hc/bilstm_1[0][0]']

 model_hc/bilstm_2 (Bidirection  (None, 365, 64)     24832       ['model_hc/dence_2[0][0]']
 al)

 add_1 (Add)                    (None, 365, 64)      0           ['model_hc/bilstm_1[0][0]',
                                                                  'model_hc/attention[0][0]',
                                                                  'model_hc/bilstm_2[0][0]']

 model_hc/add (Addition)        (None, 128)          0           ['add_1[0][0]']

 dense_1 (Dense)                (None, 5)            645         ['model_hc/add[0][0]']

==================================================================================================
Total params: 54,469
Trainable params: 54,469
Non-trainable params: 0
__________________________________________________________________________________________________