张量估计器的精度和损失为零

Question

My model's accuracy and loss are evaluating to 0.
The global steps should be 1625 but it's 1.
The acc and loss shouldn't be equal to 0 as both of them are contradicting each other.

My input function,keras estimator,train_and_evaluate are as follows:

def make_input_fn(addrs,labels,batch_size,mode):

 filename_dataset = tf.data.Dataset.from_tensor_slices((addrs,labels))     

 dataset = filename_dataset.apply(tf.contrib.data.map_and_batch(lambda 
 addrs, labels: tuple(tf.py_func(
    process, [addrs, labels], [tf.uint8, labels.dtype])),batch_size,

 num_parallel_batches=2,

 drop_remainder=False))
 if mode == tf.estimator.ModeKeys.TRAIN:
  num_epochs = None # indefinitely
  dataset = dataset.apply(tf.contrib.data.shuffle_and_repeat(buffer_size = 10000))
 else:
  num_epochs = 1
  dataset = dataset.repeat(num_epochs)

 dataset = dataset.prefetch(buffer_size=batch_size)
 images,labels = dataset.make_one_shot_iterator().get_next()
 images.set_shape([None,512,512,3])
 labels.set_shape([None,1])
 return images,labels

def keras_estimator(model_dir,config):
 base_model = Xception(weights='imagenet', include_top=False,input_shape = 
  (512,512,3),classes = 5)
 x = base_model.output
 x = GlobalAveragePooling2D()(x)

 x = Dense(1024, activation='relu')(x)
 x = Dropout(0.2)(x)
 x = Dense(256, activation='relu')(x)
 x = Dropout(0.2)(x)

 predictions = Dense(5, activation='softmax')(x)


 model = Model(inputs=base_model.input, outputs=predictions)


 for layer in base_model.layers:
   layer.trainable = False
 model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', 
       metrics=['acc'])


 estimator=tf.keras.estimator.model_to_estimator(keras_model=model,
      model_dir=model_dir,
      config=config)
 return estimator

def train_and_evaluate(model_dir):
 t_batch_size = 512
 e_batch_size = 64
 num_epochs = 25
 import pandas as pd
 df = pd.read_csv('/content/trainLabels.csv')
 from random import shuffle
 addrs = ['/content/train/train/' + str(df.iloc[i]['image']) + '.jpeg' for i 
 in range(len(df))]
 labels = df['level'].values.tolist()
 c = list(zip(addrs, labels))
 shuffle(c)
 addrs1, labels1 = zip(*c)
 train_addrs = addrs1[0 : int(0.9 * len(addrs))]
 train_labels = labels1[0 : int(0.9 * len(labels))]
 val_addrs = addrs1[ int(0.9 * len(addrs)) : ]
 val_labels = labels1[ int(0.9 * len(addrs)) : ]
 train_addrs = list(train_addrs)
 train_labels = list(train_labels)
 val_addrs = list(val_addrs)
 val_labels = list(val_labels)

 run_config = tf.estimator.RunConfig(save_checkpoints_secs=300)

 estimator = keras_estimator(model_dir,run_config)

 t_max_steps = (len(train_addrs) // t_batch_size) * num_epochs

 train_spec = tf.estimator.TrainSpec(input_fn = lambda : 
 make_input_fn(train_addrs,train_labels,
 t_batch_size,mode=tf.estimator.ModeKeys.TRAIN),max_steps = t_max_steps)

 eval_spec = tf.estimator.EvalSpec(input_fn = lambda : 
 make_input_fn(val_addrs,val_labels,
 e_batch_size,mode=tf.estimator.ModeKeys.EVAL),steps = 
 None,start_delay_secs=10,
    throttle_secs=300)


 tf.estimator.train_and_evaluate(estimator, train_spec, eval_spec)

Here are the log files:

INFO:tensorflow:Running training and evaluation locally (non-distributed). INFO:tensorflow:Start train and evaluate loop. The evaluate will happen after every checkpoint. Checkpoint frequency is determined based on RunConfig arguments: save_checkpoints_steps None or save_checkpoints_secs 300. WARNING:tensorflow:From :9: map_and_batch (from tensorflow.contrib.data.python.ops.batching) is deprecated and will be removed in a future version. Instructions for updating: Use tf.data.experimental.map_and_batch(...). WARNING:tensorflow:From :12: shuffle_and_repeat (from tensorflow.contrib.data.python.ops.shuffle_ops) is deprecated and will be removed in a future version. Instructions for updating: Use tf.data.experimental.shuffle_and_repeat(...). INFO:tensorflow:Calling model_fn. INFO:tensorflow:Done calling model_fn. INFO:tensorflow:Warm-starting with WarmStartSettings: WarmStartSettings(ckpt_to_initialize_from='/content/training/keras/keras_model.ckpt', vars_to_warm_start='.*', var_name_to_vocab_info={}, var_name_to_prev_var_name={}) INFO:tensorflow:Warm-starting from: ('/content/training/keras/keras_model.ckpt',) INFO:tensorflow:Warm-starting variable: dense/kernel; prev_var_name: Unchanged INFO:tensorflow:Warm-starting variable: dense/bias; prev_var_name: Unchanged INFO:tensorflow:Warm-starting variable: dense_1/kernel; prev_var_name: Unchanged INFO:tensorflow:Warm-starting variable: dense_1/bias; prev_var_name: Unchanged INFO:tensorflow:Warm-starting variable: dense_2/kernel; prev_var_name: Unchanged INFO:tensorflow:Warm-starting variable: dense_2/bias; prev_var_name: Unchanged INFO:tensorflow:Warm-starting variable: Adam/iterations; prev_var_name: Unchanged INFO:tensorflow:Warm-starting variable: Adam/lr; prev_var_name: Unchanged INFO:tensorflow:Warm-starting variable: Adam/beta_1; prev_var_name: Unchanged INFO:tensorflow:Warm-starting variable: Adam/beta_2; prev_var_name: Unchanged INFO:tensorflow:Warm-starting variable: Adam/decay; prev_var_name: Unchanged INFO:tensorflow:Warm-starting variable: training/Adam/Variable; prev_var_name: Unchanged INFO:tensorflow:Warm-starting variable: training/Adam/Variable_1; prev_var_name: Unchanged INFO:tensorflow:Warm-starting variable: training/Adam/Variable_2; prev_var_name: Unchanged INFO:tensorflow:Warm-starting variable: training/Adam/Variable_3; prev_var_name: Unchanged INFO:tensorflow:Warm-starting variable: training/Adam/Variable_4; prev_var_name: Unchanged INFO:tensorflow:Warm-starting variable: training/Adam/Variable_5; prev_var_name: Unchanged INFO:tensorflow:Warm-starting variable: training/Adam/Variable_6; prev_var_name: Unchanged INFO:tensorflow:Warm-starting variable: training/Adam/Variable_7; prev_var_name: Unchanged INFO:tensorflow:Warm-starting variable: training/Adam/Variable_8; prev_var_name: Unchanged INFO:tensorflow:Warm-starting variable: training/Adam/Variable_9; prev_var_name: Unchanged INFO:tensorflow:Warm-starting variable: training/Adam/Variable_10; prev_var_name: Unchanged INFO:tensorflow:Warm-starting variable: training/Adam/Variable_11; prev_var_name: Unchanged INFO:tensorflow:Warm-starting variable: training/Adam/Variable_12; prev_var_name: Unchanged INFO:tensorflow:Warm-starting variable: training/Adam/Variable_13; prev_var_name: Unchanged INFO:tensorflow:Warm-starting variable: training/Adam/Variable_14; prev_var_name: Unchanged INFO:tensorflow:Warm-starting variable: training/Adam/Variable_15; prev_var_name: Unchanged INFO:tensorflow:Warm-starting variable: training/Adam/Variable_16; prev_var_name: Unchanged INFO:tensorflow:Warm-starting variable: training/Adam/Variable_17; prev_var_name: Unchanged INFO:tensorflow:Create CheckpointSaverHook. INFO:tensorflow:Graph was finalized. INFO:tensorflow:Running local_init_op. INFO:tensorflow:Done running local_init_op. INFO:tensorflow:Saving checkpoints for 0 into /content/training/model.ckpt. INFO:tensorflow:Saving checkpoints for 1 into /content/training/model.ckpt. INFO:tensorflow:Calling model_fn. INFO:tensorflow:Done calling model_fn. INFO:tensorflow:Starting evaluation at 2018-11-05-13:21:17 INFO:tensorflow:Graph was finalized. INFO:tensorflow:Restoring parameters from /content/training/model.ckpt-1 INFO:tensorflow:Running local_init_op. INFO:tensorflow:Done running local_init_op. INFO:tensorflow:Finished evaluation at 2018-11-05-13:22:08 INFO:tensorflow:Saving dict for global step 1: acc = 0.0, global_step = 1, loss = 0.0 INFO:tensorflow:Saving 'checkpoint_path' summary for global step 1: /content/training/model.ckpt-1 INFO:tensorflow:Loss for final step: None.

Answer 1

I had this issue before. It was because that I specified the wrong directory for the data sets. Ultimately tensorflow had no input data. I hope this helps.