Dear Dr,

Thank you for your great package.

I want to do fine tuning. Because my output just has one track. But your human model has 5135 tracks. I use the seqnn_model.model transform your basenji model to keras model. Then correct the archeciture of model. But when I want to train, there are some problem.

This is my all code.

`import tensorflow as tf import numpy as np import keras import os import json from basenji import seqnn from keras.initializers import glorot_uniform from tensorflow.keras.models import Model, Sequential from tensorflow.keras.optimizers import Adam, RMSprop

Load pre-trained model

read model parameters

with open('/mnt/ruiyanhou/nfs_share2/variant_TSS/run_basenji/do_fine_tuning/params_human.json') as params_open: params = json.load(params_open)

params_model = params['model'] params_model

params_train = params['train'] params_train

model_file='/mnt/ruiyanhou/nfs_share2/variant_TSS/run_basenji/do_fine_tuning/model_human.h5' model_file

initialize model

seqnn_model = seqnn.SeqNN(params_model) #这一步是对类进行实例化 seqnn_model.restore(model_file,head_i=0 ,trunk=False) #然后调用这个类下面的方法；包括restore和build_ensemble

seqnn_model

seqnn_model.model.summary()

model = seqnn_model.model model

tf.keras.utils.plot_model(model,to_file='simple.png',show_shapes=True)

activation_layer=model.get_layer('tf.nn.gelu_30') activation_layer

activation_layer.output

base_model=Model(inputs=model.input,outputs=activation_layer.output) base_model

freeze layers which would not be trained

def print_layer_trainable(): for layer in base_model.layers: print("{0}:\t{1}".format(layer.trainable, layer.name))

print_layer_trainable()

base_model.trainable = False

for layer in base_model.layers: layer.trainable = False

print_layer_trainable()

create a new model

new_model=Sequential() new_model.add(base_model) new_last_layer=tf.keras.layers.Dense(units=1, activation="softplus") new_model.add(new_last_layer) new_model

new_model.summary()

for layer in new_model.layers: print(layer) print(layer.trainable) print(len(layer.weights)) print(len(layer.trainable_weights)) print(len(layer.non_trainable_weights))

train this model in new dataset

from basenji import trainer import pandas as pd from basenji import dataset

read datasets

data_dirs=['/mnt/ruiyanhou/nfs_share2/variant_TSS/run_basenji/run_basenji/data_out'] train_data = [] eval_data = []

for data_dir in data_dirs:

set strand pairs

targets_df = pd.read_csv('%s/targets.txt'%data_dir, sep='\t', index_col=0)

# load train data
train_data.append(dataset.SeqDataset(data_dir,
split_label='train',
batch_size=params_train['batch_size'],
shuffle_buffer=params_train.get('shuffle_buffer', 128),
mode='train'))

# load eval data
eval_data.append(dataset.SeqDataset(data_dir,
split_label='valid',
batch_size=params_train['batch_size'],
mode='eval'))

train_data

eval_data

initialize trainer

out_dir='/mnt/ruiyanhou/nfs_share2/variant_TSS/run_basenji/run_basenji/unit_2_output'

seqnn_trainer = trainer.Trainer(params_train, train_data, eval_data, out_dir)

seqnn_trainer

compile model

seqnn_trainer.compile(new_model)`

Any suggestion? Thank you for your help!

calico / basenji

How to convert the keras model to a basenji model #180