AttributeError: 'Model' object has no attribute '_in_multi_worker_mode'

[Anand2805]

trafficstars

import segmentation_models as sm from segmentation_models.metrics import iou_score from segmentation_models import Unet

import tensorflow as tf tf.keras.backend.set_image_data_format('channels_last')

model = Unet('resnet34', encoder_weights='imagenet', classes=40, activation='sigmoid') model.summary()

optim = tf.keras.optimizers.Adam(0.0001)

focal_loss = sm.losses.cce_dice_loss

model.compile(optim, focal_loss, metrics=[iou_score])

callbacks = [ tf.keras.callbacks.ModelCheckpoint('model/best_model.h5', save_weights_only=True, save_best_only=True,
mode='min', monitor='val_iou_score'), tf.keras.callbacks.ReduceLROnPlateau(monitor='val_iou_score', min_lr=0.000001,patience=2), ]

im getting the above error while training the model.

[AbtinDjavadifar]

import segmentation_models as sm from segmentation_models.metrics import iou_score from segmentation_models import Unet

import tensorflow as tf tf.keras.backend.set_image_data_format('channels_last')

model = Unet('resnet34', encoder_weights='imagenet', classes=40, activation='sigmoid') model.summary()

optim = tf.keras.optimizers.Adam(0.0001)

focal_loss = sm.losses.cce_dice_loss

model.compile(optim, focal_loss, metrics=[iou_score])

callbacks = [ tf.keras.callbacks.ModelCheckpoint('model/best_model.h5', save_weights_only=True, save_best_only=True, mode='min', monitor='val_iou_score'), tf.keras.callbacks.ReduceLROnPlateau(monitor='val_iou_score', min_lr=0.000001,patience=2), ]

im getting the above error while training the model.

Hey, could you solve this?

[eddienko]

For the moment, I am solving this with

model._in_multi_worker_mode = lambda: None