def read_data(image_name_file, image_path, size, batch_size):
"""Executes common.read_images with CornerNet_Lite arguments.
Args:
image_name_file: file with names of images
image_path: path to images
size: size of images
batch_size: size of batch
Returns: np array of shape (num_images, size, size, channels)
"""
return common.read_images(image_name_file=image_name_file,
image_path=image_path,
size=size)
#!/usr/bin/python3
import sys, os
import numpy as np
import common
# Load data
prefix = "t10k"
images = common.read_images(prefix)
labels = common.read_labels(prefix)
# Load result
try:
result_filepath = sys.argv[1]
result = np.loadtxt(result_filepath).astype("float32")
result = result.reshape([result.shape[0], 1])
except IndexError:
print("Usage: " + os.path.basename(__file__) + " <result_filepath>")
sys.exit(1)
# Get false indices
false_indices = np.argwhere(labels != result)[:, 0]
# Debugging
debug_dir = "debugging"
common.create_dir_if_not_exists(debug_dir)
for i in false_indices:
common.debug(debug_dir, i, images[i], labels[i][0], result[i][0])
import common
# Metadata
batch_size = 128
epochs = 1000
training_dir = "training"
checkpoint_format = "weights.{epoch:04d}-{val_loss:.2f}.h5"
period = 5
shift_range = 2
# Create checkpoint directory if not exists
common.create_dir_if_not_exists(training_dir)
# Load data
images = common.read_images("train")
ori_labels = common.read_labels("train")
new_labels = common.category2binary(ori_labels)
# Load test
test_images = common.read_images("t10k")
test_labels = common.category2binary(common.read_labels("t10k"))
# Create model
model = common.create_model()
# Summary model
print("=" * 80)
model.summary()
input("Press Enter to continue...")
print("=" * 80)