tensorflow模型执行程序文件：
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import numpy as np
import tensorflow as tf
import os
import json
import argparse
from tensorflow.python.platform import tf_logging
import logging as _logging
import sys as _sys
# IMAGE_SIZE = 256
# NUM_CHANNELS = 1
# PIXEL_DEPTH = 255
# NUM_LABELS = 2
# # TRAIN_SIZE = train_labels.shape[0]
# # VALIDATION_SIZE = test_labels.shape[0] # Size of the validation set.
# FILTER_SIZE = 5
# FILTER_1 = 20
# FILTER_2 = 50
# HIDDEN_NUM = 100
# LEARNING_RATE = 0.01
# SEED = 66478 # Set to None for random seed.
# BATCH_SIZE = 5
# NUM_EPOCHS = 1 # set to be 1 for quick publish
# EVAL_BATCH_SIZE = 20
# EVAL_FREQUENCY = 20 # Number of steps between evaluations.
activation = tf.nn.relu
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1, dtype=tf.float64)
return tf.Variable(initial)
def bias_variable(shape):
initial = tf.constant(0.1, shape=shape, dtype=tf.float64)
return tf.Variable(initial)
def conv2d(x, W):
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
def max_pool_2x2(x):
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1], padding='SAME')
def cnn_model_fn(features, labels, mode):
"""Model function for CNN."""
# Input Layer
# DICOM images are 256x256 pixels, and have one color channel
# print(features["x"])
print('Mohammed')
input_layer = tf.reshape(features, [-1, 256, 256, 1])
print(input_layer)
# Convolutional Layer #1
# Computes 32 features using a 5x5 filter with ReLU activation.
# Padding is added to preserve width and height.
# Input Tensor Shape: [batch_size, 256, 256, 1]
# Output Tensor Shape: [batch_size, 256, 256, 5]
conv1 = tf.layers.conv2d(
inputs=input_layer,
filters=5,
kernel_size=[5, 5],
padding="same",
activation=tf.nn.relu)
# Pooling Layer #1
# First max pooling layer with a 2x2 filter and stride of 2
# Input Tensor Shape: [batch_size, 256, 256, 5]
# Output Tensor Shape: [batch_size, 128, 128, 5]
pool1 = tf.layers.max_pooling2d(inputs=conv1, pool_size=[2, 2], strides=2)
# Convolutional Layer #2
# Computes 64 features using a 5x5 filter.
# Padding is added to preserve width and height.
# Input Tensor Shape: [batch_size, 128, 128, 5]
# Output Tensor Shape: [batch_size, 128, 128, 10]
conv2 = tf.layers.conv2d(
inputs=pool1,
filters=10,
kernel_size=[5, 5],
padding="same",
activation=tf.nn.relu)
# Pooling Layer #2
# Second max pooling layer with a 2x2 filter and stride of 2
# Input Tensor Shape: [batch_size, 128, 128, 10]
# Output Tensor Shape: [batch_size, 64, 64, 10]
pool2 = tf.layers.max_pooling2d(inputs=conv2, pool_size=[2, 2], strides=2)
# Flatten tensor into a batch of vectors
# Input Tensor Shape: [batch_size, 64, 64, 10]
# Output Tensor Shape: [batch_size, 64 * 64 * 10]
pool2_flat = tf.reshape(pool2, [-1, 64 * 64 * 10])
# Dense Layer
# Densely connected layer with 1024 neurons
# Input Tensor Shape: [batch_size, 64 * 64 * 10]
# Output Tensor Shape: [batch_size, 1024]
dense = tf.layers.dense(inputs=pool2_flat, units=1024, activation=tf.nn.relu)
# Add dropout operation; 0.6 probability that element will be kept
dropout = tf.layers.dropout(
inputs=dense, rate=0.4, training=mode == tf.estimator.ModeKeys.TRAIN)
# Logits layer
# Input Tensor Shape: [batch_size, 1024]
# Output Tensor Shape: [batch_size, 10]
logits = tf.layers.dense(inputs=dropout, units=10)
predictions = {
# Generate predictions (for PREDICT and EVAL mode)
"classes": tf.argmax(input=logits, axis=1),
# Add `softmax_tensor` to the graph. It is used for PREDICT and by the
# `logging_hook`.
"probabilities": tf.nn.softmax(logits, name="softmax_tensor")
}
if mode == tf.estimator.ModeKeys.PREDICT:
return tf.estimator.EstimatorSpec(mode=mode, predictions=predictions)
# Calculate Loss (for both TRAIN and EVAL modes)
loss = tf.losses.sparse_softmax_cross_entropy(labels=labels, logits=logits)
# Configure the Training Op (for TRAIN mode)
if mode == tf.estimator.ModeKeys.TRAIN:
data_optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.001)
train_op = data_optimizer.minimize(loss=loss,global_step=tf.train.get_global_step())
return tf.estimator.EstimatorSpec(mode=mode, loss=loss, train_op=train_op)
# Add evaluation metrics (for EVAL mode)
eval_metric_ops = {
"accuracy": tf.metrics.accuracy(
labels=labels, predictions=predictions["classes"])}
return tf.estimator.EstimatorSpec(
mode=mode, loss=loss, eval_metric_ops=eval_metric_ops)
def _load_training_data(base_dir):
x_train = np.load(os.path.join(base_dir, 'train_data.npy'))
y_train = np.load(os.path.join(base_dir, 'train_labels.npy'))
return x_train, y_train
def _load_testing_data(base_dir):
x_test = np.load(os.path.join(base_dir, 'eval_data.npy'))
y_test = np.load(os.path.join(base_dir, 'eval_labels.npy'))
return x_test, y_test
def _parse_args():
parser = argparse.ArgumentParser()
# Data, model, and output directories
# model_dir is always passed in from SageMaker. By default this is a S3 path under the default bucket.
parser.add_argument('--model_dir', type=str)
parser.add_argument('--sm-model-dir', type=str, default=os.environ.get('SM_MODEL_DIR'))
parser.add_argument('--train', type=str, default=os.environ.get('SM_CHANNEL_TRAINING'))
parser.add_argument('--hosts', type=list, default=json.loads(os.environ.get('SM_HOSTS')))
parser.add_argument('--current-host', type=str, default=os.environ.get('SM_CURRENT_HOST'))
return parser.parse_known_args()
def serving_input_fn():
inputs = {'x': tf.placeholder(tf.float32, [None, 65536])}
return tf.estimator.export.ServingInputReceiver(inputs, inputs)
if __name__ == "__main__":
args, unknown = _parse_args()
train_data, train_labels = _load_training_data(args.train)
eval_data, eval_labels = _load_testing_data(args.train)
# train_labels = tf.convert_to_tensor(train_labels)
# eval_labels = tf.convert_to_tensor(eval_labels)
# print(args.model_dir)
# Create the Estimator
mnist_classifier = tf.estimator.Estimator(
model_fn=cnn_model_fn, model_dir=args.model_dir)
# Set up logging for predictions
# Log the values in the "Softmax" tensor with label "probabilities"
tensors_to_log = {"probabilities": "softmax_tensor"}
logging_hook = tf.train.LoggingTensorHook(
tensors=tensors_to_log, every_n_iter=50)
# print({"x": train_data})
# print({"x": eval_data})
# Train the model
train_input_fn = tf.estimator.inputs.numpy_input_fn(
x=train_data,
y=train_labels,
batch_size=2,
num_epochs=None,
shuffle=True)
# Evaluate the model and print results
eval_input_fn = tf.estimator.inputs.numpy_input_fn(
x=eval_data,
y=eval_labels,
num_epochs=1,
shuffle=False)
train_spec = tf.estimator.TrainSpec(train_input_fn, max_steps=20000)
eval_spec = tf.estimator.EvalSpec(eval_input_fn)
tf.estimator.train_and_evaluate(mnist_classifier, train_spec, eval_spec)
if args.current_host == args.hosts[0]:
mnist_classifier.export_savedmodel(args.sm_model_dir, serving_input_fn)
以下是错误：
#011 [[{{node conv2d/BiasAdd}} = _MklConv2DWithBias[T=DT_DOUBLE, _kernel="MklOp", data_format="NHWC", dilations=[1, 1, 1, 1], padding="SAME", strides=[1, 1, 1, 1], use_cudnn_on_gpu=true, _device="/job:worker/replica:0/task:0/device:CPU:0"](Reshape, conv2d/kernel/read_S41, conv2d/bias/read_S51, DMT/_0, DMT/_1, DMT/_2)]]