Trax 多类神经网络错误与 Eval_task

Steps to reproduce:

Error logs:

from trax.supervised import training batch_size = 16 rnd.seed(271) train_task = training.TrainTask( labeled_data=train_generator(batch_size=batch_size, shuffle=True), loss_layer=tl.WeightedCategoryCrossEntropy(), optimizer=trax.optimizers.Adam(0.01), n_steps_per_checkpoint=10, ) eval_task = training.EvalTask( labeled_data=val_generator(batch_size=batch_size, shuffle=True), metrics=[tl.WeightedCategoryCrossEntropy(), tl.Accuracy()], ) model = classifier() output_dir = '~/model/' output_dir_expand = os.path.expanduser(output_dir) print(output_dir_expand)

GRADED FUNCTION: train_model

def train_model(classifier, train_task, eval_task, n_steps, output_dir): ''' Input: classifier - the model you are building train_task - Training task eval_task - Evaluation task n_steps - the evaluation steps output_dir - folder to save your files Output: trainer - trax trainer '''

START CODE HERE (Replace instances of 'None' with your code) # END CODE HERE

training_loop = training.Loop( classifier, # The learning model train_task, # The training task eval_task = eval_task, # The evaluation task output_dir = output_dir) # The output directory training_loop.run(n_steps = n_steps)

Return the training_loop, since it has the model.

return training_loop training_loop = train_model(model, train_task, eval_task, 100, output_dir_expand) Error code:

TypeError Traceback (most recent call last) in -----> 1 training_loop = train_model(model, train_task, eval_task, 100, output_dir_expand) in train_model(classifier, train_task, eval_task, n_steps, output_dir) 16 training_loop = training.Loop( 17 classifier, # The learning model 18 train_task, # The training task 19 eval_task = eval_task, # The 20 output_dir = output_dir) # The output directory 21 # START CODE HERE (Replace instances of 'None' with your code) 22 # END CODE HERE # 23 training_loop.run(n_steps = n_steps) 24 # Return the training_loop, since it has the model. 25 return training_loop