a long nmr sequence wavelet coefficients are input as cnn-resnet, and the corresponding nmr sequence wavelet coefficients are used as cnn-resnet18 output for denoising in python in python

main.py
import pywt
import numpy as np
import tensorflow as tf

# Load NMR sequence data here
86 chars
6 lines

main.py
# Select the appropriate wavelet function for decomposition
wavelet = pywt.Wavelet('db4')

# Decompose the NMR sequence using wavelet transform
coeffs = pywt.wavedec(nmr_seq, wavelet)
184 chars
6 lines

main.py
# Prepare the input and output data for training the CNN-ResNet18
# For example, split the data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(coeffs, nmr_seq, test_size=0.2)

# Reshape the input data to match the expected input shape of the CNN-ResNet18 model
X_train = np.asarray(X_train).reshape((X_train.shape[0], X_train.shape[1], 1))
X_test = np.asarray(X_test).reshape((X_test.shape[0], X_test.shape[1], 1))
451 chars
8 lines

main.py
# Define and train the CNN-ResNet18 model
model = tf.keras.Sequential([
    tf.keras.layers.InputLayer(input_shape=(X_train.shape[1], 1)),
    tf.keras.layers.Conv1D(filters=64, kernel_size=3, padding='same', activation='relu'),
    tf.keras.layers.MaxPooling1D(pool_size=2),
    tf.keras.layers.Conv1D(filters=128, kernel_size=3, padding='same', activation='relu'),
    tf.keras.layers.Conv1D(filters=256, kernel_size=3, padding='same', activation='relu'),
    tf.keras.layers.Conv1D(filters=512, kernel_size=3, padding='same', activation='relu'),
    tf.keras.layers.Conv1D(filters=1024, kernel_size=3, padding='same', activation='relu'),
    tf.keras.layers.UpSampling1D(size=2),
    tf.keras.layers.Conv1D(filters=512, kernel_size=3, padding='same', activation='relu'),
    tf.keras.layers.Conv1D(filters=256, kernel_size=3, padding='same', activation='relu'),
    tf.keras.layers.Conv1D(filters=128, kernel_size=3, padding='same', activation='relu'),
    tf.keras.layers.Conv1D(filters=64, kernel_size=3, padding='same', activation='relu'),
    tf.keras.layers.Conv1D(filters=1, kernel_size=1, padding='same', activation='linear')
])

model.compile(optimizer='adam', loss='mse')
model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=10, batch_size=32)
1272 chars
20 lines

main.py
# Apply the trained CNN-ResNet18 model to denoise new and unseen long NMR sequences
noisy_coeffs = pywt.wavedec(noisy_nmr_seq, wavelet)
noisy_coeffs = np.asarray(noisy_coeffs).reshape((1, noisy_coeffs.shape[0], 1))
denoised_coeffs = model.predict(noisy_coeffs)
denoised_nmr_seq = pywt.waverec(denoised_coeffs, wavelet)
319 chars
6 lines