# create image data generator object
test_image_data_generator = keras.preprocessing.image.ImageDataGenerator()
# create a generator for testing data
test_generator = CSVGenerator(
args.test_path,
args.class_file,
args.mean_image,
test_image_data_generator,
image_min_side=args.image_min_side,
image_max_side=args.image_max_side)
# start collecting results
results = []
image_ids = []
for i in range(len(test_generator.image_names)):
image = test_generator.load_image(i)
image = test_generator.preprocess_image(image)
image, scale = test_generator.resize_image(image)
# run network
_, _, detections = model.predict_on_batch(np.expand_dims(image, axis=0))
# clip to image shape
detections[:, :, 0] = np.maximum(0, detections[:, :, 0])
detections[:, :, 1] = np.maximum(0, detections[:, :, 1])
detections[:, :, 2] = np.minimum(image.shape[1], detections[:, :, 2])
detections[:, :, 3] = np.minimum(image.shape[0], detections[:, :, 3])
# correct boxes for image scale
detections[0, :, :4] /= scale
def create_tfrecords(annotations_file,
class_file,
backbone_model="resnet50",
image_min_side=800,
size=1,
savedir="./"):
"""
Args:
annotations_file: path to 6 column data in form image_path, xmin, ymin, xmax, ymax, label
backbone_model: A keras retinanet backbone
image_min_side: resized image object minimum size
size: Number of images per tfrecord
savedir: dir path to save tfrecords files
Returns:
written_files: A list of path names of written tfrecords
"""
memory_used = []
#Image preprocess function
backbone = models.backbone(backbone_model)
#filebase name
image_basename = os.path.splitext(os.path.basename(annotations_file))[0]
## Syntax checks
##Check annotations file only JPEG, PNG, GIF, or BMP are allowed.
#df = pd.read_csv(annotations_file, names=["image_path","xmin","ymin","xmax","ymax","label"])
#df['FileType'] = df.image_path.str.split('.').str[-1].str.lower()
#bad_files = df[~df['FileType'].isin(["jpeg","jpg","png","gif","bmp"])]
#if not bad_files.empty:
#raise ValueError("Check annotations file, only JPEG, PNG, GIF, or BMP are allowed, {} incorrect files found /n {}: ".format(bad_files.shape[0],bad_files.head()))
#Check dtypes, cannot use pandas, or will coerce in the presence of NAs
with open(annotations_file, 'r') as f:
reader = csv.reader(f, delimiter=',')
row = next(reader)
if row[1].count(".") > 0:
raise ValueError(
"Annotation files should be headerless with integer box, {} is not a int"
.format(row[1]))
#Create generator - because of how retinanet yields data, this should always be 1. Shape problems in the future?
train_generator = CSVGenerator(annotations_file,
class_file,
batch_size=1,
image_min_side=image_min_side,
preprocess_image=backbone.preprocess_image)
#chunk size
indices = np.arange(train_generator.size())
chunks = [
indices[i * size:(i * size) + size]
for i in range(ceil(len(indices) / size))
]
written_files = []
for chunk in chunks:
#Create tfrecord dataset and save it for output
fname = savedir + "{}_{}.tfrecord".format(image_basename, chunk[0])
written_files.append(fname)
writer = tf.io.TFRecordWriter(fname)
images = []
regression_targets = []
class_targets = []
filename = []
original_image = []
for i in chunk:
#Original image
original_image.append(train_generator.load_image(i))
batch = train_generator.__getitem__(i),
#split into images and tar gets
inputs, targets = batch[0]
#grab image, asssume batch size of 1, squeeze
images.append(inputs[0, ...])
#Grab anchor targets
regression_batch, labels_batch = targets
#grab regression anchors
#regression_batch: batch that contains bounding-box regression targets for an image & anchor states (np.array of shape (batch_size, N, 4 + 1),
#where N is the number of anchors for an image, the first 4 columns define regression targets for (x1, y1, x2, y2) and the
#last column defines anchor states (-1 for ignore, 0 for bg, 1 for fg).
regression_anchors = regression_batch[0, ...]
regression_targets.append(regression_anchors)
#grab class labels - squeeze out batch size
#From retinanet: labels_batch: batch that contains labels & anchor states (np.array of shape (batch_size, N, num_classes + 1),
#where N is the number of anchors for an image and the last column defines the anchor state (-1 for ignore, 0 for bg, 1 for fg).
labels = labels_batch[0, ...]
print("Label shape is: {}".format(labels.shape))
class_targets.append(labels)
#append filename by looking at group index
current_index = train_generator.groups[i][0]
#Grab filename and append to the full path
fname = train_generator.image_names[current_index]
fname = os.path.join(train_generator.base_dir, fname)
filename.append(fname)
for image, regression_target, class_target, fname, orig_image in zip(
images, regression_targets, class_targets, filename,
original_image):
tf_example = create_tf_example(image, regression_target,
class_target, fname, orig_image)
writer.write(tf_example.SerializeToString())
memory_used.append(psutil.virtual_memory().used / 2**30)
plt.plot(memory_used)
plt.title('Evolution of memory')
plt.xlabel('iteration')
plt.ylabel('memory used (GB)')
plt.savefig(os.path.join(savedir, "memory.png"))
return written_files
def main():
os.makedirs(RESULTS_DIR, exist_ok=True)
# os.environ["CUDA_VISIBLE_DEVICES"] = "0"
keras.backend.tensorflow_backend.set_session(get_session())
if SNAPSHOT_FILE:
snapshot_file = SNAPSHOT_FILE
else:
snapshots = os.listdir(SNAPSHOT_DIR)
if not snapshots:
raise Exception("There are no snapshots")
snapshot_file = os.path.join(SNAPSHOT_DIR,
sorted(snapshots, reverse=True)[0])
print("snapshot: {}".format(snapshot_file))
model = keras.models.load_model(
snapshot_file, custom_objects=custom_objects)
# print(model.summary())
# create image data generator object
val_image_data_generator = keras.preprocessing.image.ImageDataGenerator()
# create a generator for testing data
val_generator = CSVGenerator(
ANNOTATIONS,
CLASSES,
val_image_data_generator,
batch_size=BATCH_SIZE,
base_dir=BASE_DIR)
for image_index in range(val_generator.size()):
# load image
image = val_generator.load_image(image_index)
# copy to draw on
draw = image.copy()
draw = cv2.cvtColor(draw, cv2.COLOR_BGR2RGB)
# preprocess image for network
image = val_generator.preprocess_image(image)
image, scale = val_generator.resize_image(image)
annotations = val_generator.load_annotations(image_index)
# process image
start = time.time()
_, _, detections = model.predict_on_batch(
np.expand_dims(image, axis=0))
print("processing time: ", time.time() - start)
# compute predicted labels and scores
predicted_labels = np.argmax(detections[0, :, 4:], axis=1)
scores = detections[
0, np.arange(detections.shape[1]), 4 + predicted_labels]
# correct for image scale
detections[0, :, :4] /= scale
# visualize detections
detected = False
for idx, (label, score) in enumerate(zip(predicted_labels, scores)):
if score < 0.5:
continue
detected = True
if VISUALIZE_RESULTS:
b = detections[0, idx, :4].astype(int)
cv2.rectangle(draw, (b[0], b[1]), (b[2], b[3]), (0, 0, 255), 3)
caption = "{} {:.3f}".format(
val_generator.label_to_name(label), score)
cv2.putText(draw, caption, (b[0], b[1] - 10),
cv2.FONT_HERSHEY_PLAIN, 1.5, (0, 0, 0), 3)
cv2.putText(draw, caption, (b[0], b[1] - 10),
cv2.FONT_HERSHEY_PLAIN, 1.5, (255, 255, 255), 2)
if VISUALIZE_RESULTS and detected:
# visualize annotations
for annotation in annotations:
label = int(annotation[4])
b = annotation[:4].astype(int)
cv2.rectangle(draw, (b[0], b[1]), (b[2], b[3]), (0, 255, 0), 2)
caption = "{}".format(val_generator.label_to_name(label))
cv2.putText(draw, caption, (b[0], b[1] - 10),
cv2.FONT_HERSHEY_PLAIN, 1.5, (0, 0, 0), 3)
cv2.putText(draw, caption, (b[0], b[1] - 10),
cv2.FONT_HERSHEY_PLAIN, 1.5, (255, 255, 255), 2)
plt.figure(figsize=(15, 15))
plt.axis('off')
plt.imshow(draw)
plt.show()