问题
I have a .tfrecords file and I want to extract, see the images in the file and augment them.
I am using https://colab.research.google.com
TensorFlow version: 2.3.0
And for the following code
raw_dataset = tf.data.TFRecordDataset("*path.tfrecords")
for raw_record in raw_dataset.take(1):
example = tf.train.Example()
example.ParseFromString(raw_record.numpy())
print(example)
I am facing the following output:
features {
feature {
key: "depth"
value {
int64_list {
value: 3
}
}
}
feature {
key: "height"
value {
int64_list {
value: 333
}
}
}
feature {
key: "image_raw"
value {
bytes_list {
value:
}
}
}
feature {
key: "label"
value {
int64_list {
value: 16
}
}
}
feature {
key: "width"
value {
int64_list {
value: 500
}
}
}
}
回答1:
Here is a simple code that can extract your .tfrecord images as .png format.
To run next codes you need to install one time pip modules through pip install tensorflow tensorflow_addons pillow numpy matplotlib.
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
import tensorflow as tf, PIL.Image, numpy as np
raw_dataset = tf.data.TFRecordDataset('max_32_set.tfrecords')
for i, raw_record in enumerate(raw_dataset.take(3)):
example = tf.train.Example()
example.ParseFromString(raw_record.numpy())
info = {}
for k, v in example.features.feature.items():
if k == 'image_raw':
info[k] = v.bytes_list.value[0]
elif k in ['depth', 'height', 'width']:
info[k] = v.int64_list.value[0]
img_arr = np.frombuffer(info['image_raw'], dtype = np.uint8).reshape(
info['height'], info['width'], info['depth']
)
# You can use img_arr numpy array above to directly augment/preprocess
# your image without saving it to .png.
img = PIL.Image.fromarray(img_arr)
img.save(f'max_32_set.tfrecords.{str(i).zfill(5)}.png')
First image from dataset:
Below is code for drawing number of images per each label. Labels inside max_32_set.tfrecords file are represented as integers (not string names), probably names of labels are located in separate small file with meta information about dataset.
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
import tensorflow as tf, numpy as np, matplotlib.pyplot as plt
raw_dataset = tf.data.TFRecordDataset('max_32_set.tfrecords')
labels_cnts = {}
for i, raw_record in enumerate(raw_dataset.as_numpy_iterator()):
example = tf.train.Example()
example.ParseFromString(raw_record)
info = {}
for k, v in example.features.feature.items():
if k == 'label':
info[k] = v.int64_list.value[0]
labels_cnts[info['label']] = labels_cnts.get(info['label'], 0) + 1
x, y = zip(*sorted(labels_cnts.items(), key = lambda e: e[0]))
plt.xlabel('label')
plt.ylabel('num images')
plt.plot(x, y)
plt.xticks(x)
plt.show()
Plot for max_32_set.tfrecords:
Next code does augmentation using gaussian noise and gaussian blur, augmented tfrecord dataset is saved to max_32_set.augmented.tfrecords file:
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
import tensorflow as tf, tensorflow_addons as tfa, PIL.Image, numpy as np, math
c_inp_fname = 'max_32_set.tfrecords'
c_out_fname = 'max_32_set.augmented.tfrecords'
c_augment_types = ('noise', 'blur', 'noise_blur', 'noise_blur_mirror')
c_res_class_size = None # If None then auto configured to maximal class size
def calc_labels():
raw_dataset = tf.data.TFRecordDataset(c_inp_fname)
cnts, labels = {}, []
for i, raw_record in enumerate(raw_dataset):
example = tf.train.Example()
example.ParseFromString(raw_record.numpy())
label = example.features.feature['label'].int64_list.value[0]
cnts[label] = cnts.get(label, 0) + 1
labels.append(label)
return cnts, labels
def img_gen():
raw_dataset = tf.data.TFRecordDataset(c_inp_fname)
for i, raw_record in enumerate(raw_dataset):
example = tf.train.Example()
example.ParseFromString(raw_record.numpy())
info = {}
for k, v in example.features.feature.items():
if k == 'image_raw':
info[k] = v.bytes_list.value[0]
elif k in ['depth', 'height', 'width']:
info[k] = v.int64_list.value[0]
img_arr = np.frombuffer(info['image_raw'], dtype = np.uint8).reshape(
info['height'], info['width'], info['depth']
)
yield example, img_arr
def gaussian_noise(inp, stddev):
noise = tf.random.normal(shape = tf.shape(inp), mean = 0.0, stddev = stddev, dtype = inp.dtype)
return inp + noise
def augment(a, cnt):
min_noise_stddev, max_noise_stddev = 5., 20.
blur_kern, min_blur_stddev, max_blur_stddev = 3, 1., 5.
assert cnt >= 1
pad_a = lambda x: np.pad(x, (
(0, 2 ** math.ceil(math.log(x.shape[0]) / math.log(2)) - x.shape[0]),
(0, 2 ** math.ceil(math.log(x.shape[1]) / math.log(2)) - x.shape[1]),
(0, 0)), constant_values = 0)
post_a = lambda x: np.clip(x[:a.shape[0], :a.shape[1]], 0, 255).astype(np.uint8)
yield 'orig', a
cnt -= 1
res = []
fcnt = math.ceil(cnt / len(c_augment_types))
linsp = lambda l, r, c: [(l + (i + 1) * (r - l) / (c + 1)) for i in range(c)]
for noise_stddev, blur_stddev in zip(linsp(min_noise_stddev, max_noise_stddev, fcnt), linsp(min_blur_stddev, max_blur_stddev, fcnt)):
if 'noise' in c_augment_types:
#yield 'noise', post_a(tf.keras.layers.GaussianNoise(stddev = noise_stddev)(prep_a, training = True).numpy())
res.append(('noise', post_a(gaussian_noise(a.astype(np.float32), stddev = noise_stddev).numpy())))
if 'blur' in c_augment_types:
res.append(('blur', post_a(tfa.image.gaussian_filter2d(pad_a(a).astype(np.float32), filter_shape = blur_kern, sigma = blur_stddev).numpy())))
if 'noise_blur' in c_augment_types or 'noise_blur_mirror' in c_augment_types:
nbr = post_a(tfa.image.gaussian_filter2d(
pad_a(gaussian_noise(a.astype(np.float32), stddev = noise_stddev).numpy()),
filter_shape = blur_kern, sigma = blur_stddev).numpy())
if 'noise_blur' in c_augment_types:
res.append(('noise_blur', nbr))
if 'noise_blur_mirror' in c_augment_types:
res.append(('noise_blur_mirror', tf.image.flip_left_right(nbr).numpy().astype(np.uint8)))
assert cnt <= len(res) <= cnt + len(c_augment_types), (cnt, len(res), len(c_augment_types))
yield from res[:cnt]
def process():
labels_cnts, labels = calc_labels()
max_class_size = max(labels_cnts.values())
if c_res_class_size is not None:
assert max_class_size <= c_res_class_size, f'Maximal class size is {max_class_size}, while requested res class size is smaller, {c_res_class_size}!'
class_size = c_res_class_size
else:
class_size = max_class_size
cur_labels_cnts = {}
for iimg, (proto, imga) in enumerate(img_gen()):
label = proto.features.feature['label'].int64_list.value[0]
cur_labels_cnts[label] = cur_labels_cnts.get(label, 0) + 1
need_cnt = class_size // labels_cnts[label] + int(cur_labels_cnts[label] <= class_size % labels_cnts[label])
for iaug, (taug, aug) in enumerate(augment(imga, need_cnt)):
#PIL.Image.fromarray(aug).save(f'max_32_set.tfrecords.aug.{str(iimg).zfill(5)}.{iaug}_{taug}.png')
protoc = type(proto)()
protoc.ParseFromString(proto.SerializeToString())
protoc.features.feature['image_raw'].bytes_list.value[0] = aug.tobytes()
yield protoc.SerializeToString()
if (iimg % 10) == 0:
print(iimg, ' ', sep = '', end = '', flush = True)
def main():
assert tf.executing_eagerly()
tf.data.experimental.TFRecordWriter(c_out_fname).write(
tf.data.TFRecordDataset.from_generator(process, tf.string)
)
main()
Example augmented images:
Original:
Noised:
Blurred:
Noised-blurred:
Noised-blurred-mirrored:
Number of images per label after augmentation (exactly balanced 30 images per label):
Same augmentation as above but for the case of input and output folders with labeled images, instead of TFRecordDataset, change c_inp_dir and c_out_dir to your folders paths:
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
import tensorflow as tf, tensorflow_addons as tfa, PIL.Image, numpy as np, math, matplotlib.pyplot as plt
c_inp_dir = './images/'
c_out_dir = './images_out/'
c_augment_types = ('noise', 'blur', 'noise_blur', 'noise_blur_mirror')
c_res_class_size = None # If None then auto configured to maximal class size
def calc_labels(dirn = None):
if dirn is None:
dirn = c_inp_dir
cnts, labels = {}, []
for label in sorted(os.listdir(f'{dirn}')):
label = int(label)
labels.append(label)
cnts[label] = len(os.listdir(f'{dirn}/{label}/'))
return cnts, labels
def img_gen():
cnts = {}
for label in sorted(os.listdir(c_inp_dir)):
label = int(label)
for fname in sorted(os.listdir(f'{c_inp_dir}/{label}/')):
img_arr = np.array(PIL.Image.open(f'{c_inp_dir}/{label}/{fname}'))
yield label, img_arr, fname
def gaussian_noise(inp, stddev):
noise = tf.random.normal(shape = tf.shape(inp), mean = 0.0, stddev = stddev, dtype = inp.dtype)
return inp + noise
def augment(a, cnt):
min_noise_stddev, max_noise_stddev = 5., 20.
blur_kern, min_blur_stddev, max_blur_stddev = 3, 1., 5.
assert cnt >= 1
pad_a = lambda x: np.pad(x, (
(0, 2 ** math.ceil(math.log(x.shape[0]) / math.log(2)) - x.shape[0]),
(0, 2 ** math.ceil(math.log(x.shape[1]) / math.log(2)) - x.shape[1]),
(0, 0)), constant_values = 0)
post_a = lambda x: np.clip(x[:a.shape[0], :a.shape[1]], 0, 255).astype(np.uint8)
yield 'orig', a
cnt -= 1
res = []
fcnt = math.ceil(cnt / len(c_augment_types))
linsp = lambda l, r, c: [(l + (i + 1) * (r - l) / (c + 1)) for i in range(c)]
for noise_stddev, blur_stddev in zip(linsp(min_noise_stddev, max_noise_stddev, fcnt), linsp(min_blur_stddev, max_blur_stddev, fcnt)):
if 'noise' in c_augment_types:
#yield 'noise', post_a(tf.keras.layers.GaussianNoise(stddev = noise_stddev)(prep_a, training = True).numpy())
res.append(('noise', post_a(gaussian_noise(a.astype(np.float32), stddev = noise_stddev).numpy())))
if 'blur' in c_augment_types:
res.append(('blur', post_a(tfa.image.gaussian_filter2d(pad_a(a).astype(np.float32), filter_shape = blur_kern, sigma = blur_stddev).numpy())))
if 'noise_blur' in c_augment_types or 'noise_blur_mirror' in c_augment_types:
nbr = post_a(tfa.image.gaussian_filter2d(
pad_a(gaussian_noise(a.astype(np.float32), stddev = noise_stddev).numpy()),
filter_shape = blur_kern, sigma = blur_stddev).numpy())
if 'noise_blur' in c_augment_types:
res.append(('noise_blur', nbr))
if 'noise_blur_mirror' in c_augment_types:
res.append(('noise_blur_mirror', tf.image.flip_left_right(nbr).numpy().astype(np.uint8)))
assert cnt <= len(res) <= cnt + len(c_augment_types), (cnt, len(res), len(c_augment_types))
yield from res[:cnt]
def process():
labels_cnts, labels = calc_labels()
max_class_size = max(labels_cnts.values())
if c_res_class_size is not None:
assert max_class_size <= c_res_class_size, f'Maximal class size is {max_class_size}, while requested res class size is smaller, {c_res_class_size}!'
class_size = c_res_class_size
else:
class_size = max_class_size
cur_labels_cnts = {}
for iimg, (label, imga, fname) in enumerate(img_gen()):
os.makedirs(f'{c_out_dir}/{label}/', exist_ok = True)
cur_labels_cnts[label] = cur_labels_cnts.get(label, 0) + 1
need_cnt = class_size // labels_cnts[label] + int(cur_labels_cnts[label] <= class_size % labels_cnts[label])
for iaug, (taug, aug) in enumerate(augment(imga, need_cnt)):
PIL.Image.fromarray(aug).save(f'{c_out_dir}/{label}/{fname}.{iaug}_{taug}.png')
if (iimg % 10) == 0:
print(iimg, ' ', sep = '', end = '', flush = True)
def plot_cnts(dirn):
labels_cnts = calc_labels(dirn)[0]
x, y = zip(*sorted(labels_cnts.items(), key = lambda e: e[0]))
plt.xlabel('label')
plt.ylabel('num images')
plt.plot(x, y)
plt.xticks(x)
plt.show()
def main():
process()
plot_cnts(c_inp_dir)
plot_cnts(c_out_dir)
main()
来源：https://stackoverflow.com/questions/65007191/how-to-read-decode-tfrecords-file-see-the-images-inside-and-do-augmentation