def process_batch(images):
"""
Uploads a batch of images to Custom Vision.
"""
batch = ImageFileCreateBatch(images=images)
# Limited to 64 images and 20 tags per batch.
upload_result = trainer.create_images_from_files(project_id=project_id,
batch=batch)
num_duplicates = 0
error_results = []
for result in upload_result.images:
if result.status == ImageCreateStatus.ok_duplicate: # Ignore errors indicating duplicate images
num_duplicates += 1
elif result.status != ImageCreateStatus.ok:
error_results.append(result)
if not upload_result.is_batch_successful and len(error_results) > 0:
message = "Batch did not upload successfully!"
for result in error_results:
message += f"""
url: {result.source_url}
-- status: {result.status}
"""
raise Exception(message)
elif num_duplicates > 0:
print(
f"Batch uploaded successfully. Ignoring {num_duplicates} duplicates."
)
else:
# print("Batch uploaded successfully.")
pass
def main():
"""
Training for object detection with Azure Custom Vision
"""
args = parse_args()
config = json.load(open(args.config, "r"))
credentials = ApiKeyCredentials(in_headers={"Training-key": config["training_key"]})
trainer = CustomVisionTrainingClient(config["ENDPOINT"], credentials)
print("Creating project...")
# Find the object detection domain
obj_detection_domain = next(
domain
for domain in trainer.get_domains()
if domain.type == "ObjectDetection" and domain.name == "General"
)
project = trainer.create_project(
config["project_name"], domain_id=obj_detection_domain.id
)
# ======================================================================================
print("Adding images...")
image_folder = config["image_folder"]
annotations = json.load(open("annotation.json", "r"))
tagged_images_with_regions = []
for label in annotations.keys():
tagged_images_with_regions += add_image(
trainer, label, project.id, annotations[label], image_folder
)
upload_result = trainer.create_images_from_files(
project.id, ImageFileCreateBatch(images=tagged_images_with_regions)
)
if not upload_result.is_batch_successful:
print("Image batch upload failed.")
for image in upload_result.images:
print("Image status: ", image.status)
# ======================================================================================
print("Training...")
publish_iteration_name = config["publish_iteration_name"]
prediction_resource_id = config["prediction_resource_id"]
iteration = trainer.train_project(project.id)
while iteration.status != "Completed":
iteration = trainer.get_iteration(project.id, iteration.id)
print("Training status: " + iteration.status)
time.sleep(1)
# The iteration is now trained. Publish it to the project endpoint
trainer.publish_iteration(
project.id, iteration.id, publish_iteration_name, prediction_resource_id
)
print("Done!")
def Upload_Images(folder):
print("Uploading images...")
# Get the tags defined in the project
tags = training_client.get_tags(custom_vision_project.id)
# Create a list of images with tagged regions
tagged_images_with_regions = []
# Get the images and tagged regions from the JSON file
with open('tagged-images.json', 'r') as json_file:
tagged_images = json.load(json_file)
for image in tagged_images['files']:
# Get the filename
file = image['filename']
# Get the tagged regions
regions = []
for tag in image['tags']:
tag_name = tag['tag']
# Look up the tag ID for this tag name
tag_id = next(t for t in tags if t.name == tag_name).id
# Add a region for this tag using the coordinates and dimensions in the JSON
regions.append(
Region(tag_id=tag_id,
left=tag['left'],
top=tag['top'],
width=tag['width'],
height=tag['height']))
# Add the image and its regions to the list
with open(os.path.join(folder, file), mode="rb") as image_data:
tagged_images_with_regions.append(
ImageFileCreateEntry(name=file,
contents=image_data.read(),
regions=regions))
# Upload the list of images as a batch
upload_result = training_client.create_images_from_files(
custom_vision_project.id,
ImageFileCreateBatch(images=tagged_images_with_regions))
# Check for failure
if not upload_result.is_batch_successful:
print("Image batch upload failed.")
for image in upload_result.images:
print("Image status: ", image.status)
else:
print("Images uploaded.")
def _upload_one_batch_training_images(self, tagged_images_with_regions):
"""
Upload one batch (maximum 64) training images to Azure Custom Vision Object Detection.
Only for internal use with in this class.
Args:
----
tagged_images_with_regions: list of ImageFileCreateEntry
"""
upload_result = self.trainer.create_images_from_files(
self.project_id,
ImageFileCreateBatch(images=tagged_images_with_regions))
if not upload_result.is_batch_successful:
print("Image batch upload failed.")
for image in upload_result.images:
print("Image status: ", image.status)
return
def main(self) -> None:
dataset_path = os.path.join(os.path.dirname(__file__),
"../../../dataset")
existing_image_count = self.trainer.get_image_count(
project_id=self.project.id)
file_number = existing_image_count
self.files_to_upload = self.files_to_upload[file_number:]
for file_name in self.files_to_upload:
tagged_images_with_regions = []
annotations: list = self._read_annotation_file(
annotation_path=os.path.join(dataset_path, "annotations",
file_name + ".txt"), )
image_bytes: bytes = read_and_resize_image(
image_path=os.path.join(dataset_path, "images",
file_name + ".JPG"),
max_byte_size=self.max_byte_size,
)
print(f"Image {file_name} is {len(image_bytes)} bytes")
tagged_images_with_regions.append(
ImageFileCreateEntry(name=file_name,
contents=image_bytes,
regions=annotations))
print("Upload images...")
upload_result = self.trainer.create_images_from_files(
self.project.id,
ImageFileCreateBatch(images=tagged_images_with_regions))
if not upload_result.is_batch_successful:
print("Image batch upload failed.")
for image in upload_result.images:
print("Image status: ", image.status)
exit(-1)
print(
f"Uploaded file number {file_number+1} of {len(self.files_to_upload)}"
)
file_number += 1
for file_name in scissors_image_regions.keys():
x, y, w, h = scissors_image_regions[file_name]
regions = [
Region(tag_id=scissors_tag.id, left=x, top=y, width=w, height=h)
]
with open(base_image_location + "images/scissors/" + file_name + ".jpg",
mode="rb") as image_contents:
tagged_images_with_regions.append(
ImageFileCreateEntry(name=file_name,
contents=image_contents.read(),
regions=regions))
upload_result = trainer.create_images_from_files(
project.id, ImageFileCreateBatch(images=tagged_images_with_regions))
if not upload_result.is_batch_successful:
print("Image batch upload failed.")
for image in upload_result.images:
print("Image status: ", image.status)
exit(-1)
print("Training...")
iteration = trainer.train_project(project.id)
while iteration.status != "Completed":
iteration = trainer.get_iteration(project.id, iteration.id)
print("Training status: " + iteration.status)
time.sleep(1)
# The iteration is now trained. Publish it to the project endpoint
trainer.publish_iteration(project.id, iteration.id, publish_iteration_name,
image_list.append(
ImageFileCreateEntry(name=file_name,
contents=image_contents.read(),
tag_ids=[hemlock_tag.id]))
for image_num in range(1, 11):
file_name = "japanese_cherry_{}.jpg".format(image_num)
with open(base_image_location + "images/Japanese Cherry/" + file_name,
"rb") as image_contents:
image_list.append(
ImageFileCreateEntry(name=file_name,
contents=image_contents.read(),
tag_ids=[cherry_tag.id]))
upload_result = trainer.create_images_from_files(
project.id, ImageFileCreateBatch(images=image_list))
if not upload_result.is_batch_successful:
print("Image batch upload failed.")
for image in upload_result.images:
print("Image status: ", image.status)
exit(-1)
# </snippet_upload>
# <snippet_train>
print("Training...")
iteration = trainer.train_project(project.id)
while (iteration.status != "Completed"):
iteration = trainer.get_iteration(project.id, iteration.id)
print("Training status: " + iteration.status)
time.sleep(1)
print("Adding images...")
image_list = []
for image_num in range(1, 11):
file_name = "hemlock_{}.jpg".format(image_num)
with open(base_image_location + "images/Hemlock/" + file_name, "rb") as image_contents:
image_list.append(ImageFileCreateEntry(name=file_name, contents=image_contents.read(), tag_ids=[hemlock_tag.id]))
for image_num in range(1, 11):
file_name = "japanese_cherry_{}.jpg".format(image_num)
with open(base_image_location + "images/Japanese Cherry/" + file_name, "rb") as image_contents:
image_list.append(ImageFileCreateEntry(name=file_name, contents=image_contents.read(), tag_ids=[cherry_tag.id]))
upload_result = trainer.create_images_from_files(project.id, ImageFileCreateBatch(images=image_list))
if not upload_result.is_batch_successful:
print("Image batch upload failed.")
for image in upload_result.images:
print("Image status: ", image.status)
exit(-1)
# </snippet_upload>
# <snippet_train>
print ("Training...")
iteration = trainer.train_project(project.id)
while (iteration.status != "Completed"):
iteration = trainer.get_iteration(project.id, iteration.id)
print ("Training status: " + iteration.status)
time.sleep(1)
dir_ = os.path.join(base_image_location, label_, mode_)
names_ = os.listdir(dir_)
names_ = [os.path.join(dir_, nm_) for nm_ in names_]
names_ = [nm_ for nm_ in names_ if os.path.isfile(nm_)]
filenames[label_][mode_] = names_
for nm_ in names_:
with open(nm_, 'rb') as img_:
images[label_][mode_].append(
ImageFileCreateEntry(name=nm_,
contents=img_.read(),
tag_ids=[tag_.id]))
#upload the training data to azure
upload_result = trainer.create_images_from_files(
project.id,
ImageFileCreateBatch(images=images['seamus']['train'] +
images['finley']['train']))
if not upload_result.is_batch_successful:
print("Image batch upload failed.")
for image in upload_result.images:
print("Image status: ", image.status)
exit(-1)
#train! It's as simple as that. Might take a few minutes...
print("Training...")
iteration = trainer.train_project(project.id)
while (iteration.status != "Completed"):
iteration = trainer.get_iteration(project.id, iteration.id)
print("Training status: " + iteration.status)
print("Waiting 10 seconds...")
time.sleep(10)
tag_ids=[positive_tag.id]))
for filename in os.listdir(args["noncovid"]):
img_path = os.path.sep.join([args["noncovid"], filename])
with open(img_path, "rb") as image_contents:
image_list.append(
ImageFileCreateEntry(name=filename,
contents=image_contents.read(),
tag_ids=[negative_tag.id]))
# Azure allows uploading 64 images per batch at once
for i in range(0, len(image_list), 64):
print("[INFO] Uploading batch: ", i)
batch = image_list[i:i + 64]
upload_result = trainer.create_images_from_files(
project.id, ImageFileCreateBatch(images=batch))
if not upload_result.is_batch_successful:
print("Image batch upload failed.")
for image in upload_result.images:
print("Image status: ", image.status)
# Train model and publish
print("[INFO] Training...")
iteration = trainer.train_project(project.id)
while (iteration.status != "Completed"):
iteration = trainer.get_iteration(project.id, iteration.id)
print("[INFO] Training status: " + iteration.status)
time.sleep(1)
# The iteration is now trained. Publish it to the project endpoint
trainer.publish_iteration(project.id, iteration.id, publish_iteration_name,
if classification == 'with_mask':
mask_list.append(name)
image_list.append(
ImageFileCreateEntry(name=name + '.png',
contents=img_f.read(),
tag_ids=[mask_tag.id]))
elif classification == 'without_mask':
no_mask_list.append(name)
image_list.append(
ImageFileCreateEntry(name=name + '.png',
contents=img_f.read(),
tag_ids=[nomask_tag.id]))
print(f"\t{len(mask_list)} photos with mask")
print(f"\t{len(no_mask_list)} photos without mask")
print("Uploading tagged images...")
# split image list into smaller portions coz batch can have max 64 images
for batch_idx in range(0, len(image_list), 64):
print(f"\tUploading batch number {int(batch_idx / 64) + 1}...")
upload_result = trainer.create_images_from_files(
project.id,
ImageFileCreateBatch(images=image_list[batch_idx:batch_idx + 64]))
if not upload_result.is_batch_successful:
print("Image batch upload failed.")
for image in upload_result.images:
print("Image status: ", image.status)
print("Upload finished.")