def des():
# Function to nicely print segmentation results with
# colorbar showing class names
def discrete_matshow(data, labels_names=[], title=""):
fig_size = [7, 6]
plt.rcParams["figure.figsize"] = fig_size
# get discrete colormap
cmap = plt.get_cmap('Paired', np.max(data) - np.min(data) + 1)
# set limits .5 outside true range
mat = plt.matshow(data,
cmap=cmap,
vmin=np.min(data) - .5,
vmax=np.max(data) + .5)
# tell the colorbar to tick at integers
cax = plt.colorbar(mat,
ticks=np.arange(np.min(data),
np.max(data) + 1))
# The names to be printed aside the colorbar
if labels_names:
cax.ax.set_yticklabels(labels_names)
if title:
plt.suptitle(title, fontsize=15, fontweight='bold')
plt.show()
with tf.Graph().as_default():
url = ("https://upload.wikimedia.org/wikipedia/commons/d/d9/"
"First_Student_IC_school_bus_202076.jpg")
image_string = urllib2.urlopen(url).read()
image = tf.image.decode_jpeg(image_string, channels=3)
# Convert image to float32 before subtracting the
# mean pixel value
image_float = tf.to_float(image, name='ToFloat')
# Subtract the mean pixel value from each pixel
processed_image = _mean_image_subtraction(image_float,
[_R_MEAN, _G_MEAN, _B_MEAN])
input_image = tf.expand_dims(processed_image, 0)
with slim.arg_scope(vgg.vgg_arg_scope()):
# spatial_squeeze option enables to use network in a fully
# convolutional manner
logits, _ = vgg.vgg_16(input_image,
num_classes=1000,
is_training=False,
spatial_squeeze=False)
# For each pixel we get predictions for each class
# out of 1000. We need to pick the one with the highest
# probability. To be more precise, these are not probabilities,
# because we didn't apply softmax. But if we pick a class
# with the highest value it will be equivalent to picking
# the highest value after applying softmax
print logits
pred = tf.argmax(logits, axis=3)
# pred = tf.expand_dims(pred,axis=-1)
# pred = slim.conv2d_transpose(pred,num_outputs=1,kernel_size=4,stride=2,weights_initializer=tf.constant_initializer(1))
print pred
init_fn = slim.assign_from_checkpoint_fn(
'vgg_16.ckpt', slim.get_model_variables('vgg_16'))
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
init_fn(sess)
segmentation, np_image, np_logits = sess.run([pred, image, logits])
# Remove the first empty dimension
print segmentation
print segmentation.shape
print np_logits.shape
segmentation = np.squeeze(segmentation)
names = imagenet.create_readable_names_for_imagenet_labels()
# Let's get unique predicted classes (from 0 to 1000) and
# relable the original predictions so that classes are
# numerated starting from zero
unique_classes, relabeled_image = np.unique(segmentation,
return_inverse=True)
segmentation_size = segmentation.shape
print segmentation_size
relabeled_image = relabeled_image.reshape(segmentation_size)
# Show the downloaded image
plt.figure()
plt.imshow(np_image.astype(np.uint8))
plt.suptitle("Input Image", fontsize=14, fontweight='bold')
plt.axis('off')
plt.show()
discrete_matshow(data=relabeled_image,
labels_names=[],
title="Segmentation")
upsampled_logits = upsample_tf(factor=32, input_img=np_logits.squeeze())
upsampled_predictions = upsampled_logits.squeeze().argmax(axis=2)
unique_classes, relabeled_image = np.unique(upsampled_predictions,
return_inverse=True)
relabeled_image = relabeled_image.reshape(upsampled_predictions.shape)
labels_names = []
for index, current_class_number in enumerate(unique_classes):
labels_names.append(str(index) + ' ' + names[current_class_number + 1])
# Show the downloaded image
plt.figure()
plt.imshow(np_image.astype(np.uint8))
plt.suptitle("Input Image", fontsize=14, fontweight='bold')
plt.axis('off')
plt.show()
discrete_matshow(data=relabeled_image,
labels_names=labels_names,
title="Segmentation")
mat = plt.matshow(img, cmap=cmap, vmin=minval - 0.5, vmax=maxval + 0.5)
#定义colorbar
cax = plt.colorbar(mat, ticks=np.arange(minval, maxval + 1), shrink=2)
# 添加类别名称
if labels_str:
cax.ax.set_yticklabels(labels_str)
if title:
plt.suptitle(title, fontsize=14, fontweight='bold')
input_imgs = tf.placeholder("float", [None, None, 3])
# 每个像素减去像素的均值
processed_image = _mean_image_subtraction(input_imgs,
[_R_MEAN, _G_MEAN, _B_MEAN])
input_image = tf.expand_dims(processed_image, 0)
#print(input_image.shape)
with slim.arg_scope(
vgg.vgg_arg_scope()): # spatial_squeeze选项指定是否压缩结果的空间维度将不必要的空间维度删除
logits, _ = vgg.vgg_19(input_image,
num_classes=1000,
is_training=False,
spatial_squeeze=False)
pred = tf.argmax(logits, dimension=3)
init_fn = slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_dir, 'vgg_19.ckpt'),
slim.get_model_variables('vgg_19'))
url = ("https://upload.wikimedia.org/wikipedia/commons/d/d9/"
"First_Student_IC_school_bus_202076.jpg")
# Open specified url and load image as a string
image_string = urllib2.urlopen(url).read()
# Decode string into matrix with intensity values
image = tf.image.decode_jpeg(image_string, channels=3)
# Convert image to float32 before subtracting the
# mean pixel value
image_float = tf.to_float(image, name='ToFloat')
# Subtract the mean pixel value from each pixel
mean_centered_image = _mean_image_subtraction(image_float,
[_R_MEAN, _G_MEAN, _B_MEAN])
processed_images = tf.expand_dims(mean_centered_image, 0)
upsample_filter_tensor = tf.constant(upsample_filter_np)
# Define the model that we want to use -- specify to use only two classes at the last layer
with slim.arg_scope(vgg.vgg_arg_scope()):
logits, end_points = vgg.vgg_16(processed_images,
num_classes=2,
is_training=False,
spatial_squeeze=False,
fc_conv_padding='SAME')
downsampled_logits_shape = tf.shape(logits)
res = tf.nn.conv2d_transpose(
expanded_img,
upsample_filter_np,
output_shape=[1, new_height, new_width, number_of_classes],
strides=[1, factor, factor, 1])
res = sess.run(res)
return np.squeeze(res)
with tf.Graph().as_default():
image = tf.image.decode_jpeg(tf.read_file("apple.jpg"), channels=3)
image = tf.image.resize_images(image, [224, 224])
# 减去均值之前，将像素值转为32位浮点
image_float = tf.to_float(image, name='ToFloat')
# 每个像素减去像素的均值
processed_image = _mean_image_subtraction(image_float,
[_R_MEAN, _G_MEAN, _B_MEAN])
input_image = tf.expand_dims(processed_image, 0)
with slim.arg_scope(vgg.vgg_arg_scope()):
logits, endpoints = vgg.vgg_16(input_image,
num_classes=1000,
is_training=False,
spatial_squeeze=False)
pred = tf.argmax(logits, dimension=3) #对输出层进行逐个比较，取得不同层同一位置中最大的概率所对应的值
init_fn = slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_path, 'vgg_16.ckpt'),
slim.get_model_variables('vgg_16'))
with tf.Session() as sess:
init_fn(sess)
fcn8s, fcn16s, fcn32s = sess.run([
endpoints["vgg_16/pool3"], endpoints["vgg_16/pool4"],