def test_classification_json():
task = Tasks.CLASSIFICATION
image_size = (120, 160)
classes = ("aaa", "bbb")
params = {
"task": task,
"classes": classes,
"image_size": image_size,
"data_format": "NCHW",
}
batch_size = 2
inputs = np.random.uniform(size=[batch_size, len(classes)])
raw_images = np.zeros((batch_size, 320, 280, 3), dtype=np.uint8)
image_files = ["dummy.png", "dumpy_2.pny"]
call = JsonOutput(**params)
json_output = call(inputs, raw_images, image_files)
output = json.loads(json_output)
assert output["classes"] == [{"id": i, "name": name} for i, name in enumerate(classes)]
assert output["task"] == str(task.value)
results = output["results"]
assert [result["file_path"] for result in results] == image_files
for i in range(batch_size):
predictions = results[i]["prediction"]
assert [prediction["probability"] for prediction in predictions] == inputs[i, :].astype(str).tolist()
def test_object_detection_json():
task = Tasks.OBJECT_DETECTION
image_size = (120, 160)
classes = ("aaa", "bbb")
params = {
"task": task,
"classes": classes,
"image_size": image_size,
"data_format": "NCHW",
}
batch_size = 2
box_sizes = (3, 5)
boxes_1 = np.concatenate([
np.random.randint(120, size=(box_sizes[0], 4)),
np.random.randint(len(classes), size=(box_sizes[0], 1)),
np.random.uniform(size=(box_sizes[0], 1)),
], axis=1)
boxes_2 = np.concatenate([
np.random.randint(120, size=(box_sizes[1], 4)),
np.random.randint(len(classes), size=(box_sizes[1], 1)),
np.random.uniform(size=(box_sizes[1], 1)),
], axis=1)
inputs = [boxes_1, boxes_2]
raw_images = np.zeros((batch_size, 320, 280, 3), dtype=np.uint8)
image_files = ["dummy.png", "dumpy_2.pny"]
call = JsonOutput(**params)
json_output = call(inputs, raw_images, image_files)
output = json.loads(json_output)
assert output["classes"] == [{"id": i, "name": name} for i, name in enumerate(classes)]
assert output["task"] == str(task.value)
results = output["results"]
assert [result["file_path"] for result in results] == image_files
for i in range(batch_size):
predictions = results[i]["prediction"]
assert [prediction["score"] for prediction in predictions] == inputs[i][:, 5].astype(str).tolist()
assert [prediction["class"]["id"] for prediction in predictions] == inputs[i][:, 4].astype(int).tolist()
resized_boxes = np.stack([
inputs[i][:, 0] * 280 / image_size[1],
inputs[i][:, 1] * 320 / image_size[0],
inputs[i][:, 2] * 280 / image_size[1],
inputs[i][:, 3] * 320 / image_size[0],
], axis=1)
assert np.allclose([prediction["box"] for prediction in predictions], resized_boxes)
def test_semantic_segmentation_json():
task = Tasks.SEMANTIC_SEGMENTATION
image_size = (120, 160)
classes = ("aaa", "bbb")
params = {
"task": task,
"classes": classes,
"image_size": image_size,
"data_format": "NCHW",
}
batch_size = 2
predict = np.random.uniform(size=(batch_size, len(classes), image_size[0], image_size[1]))
raw_images = np.zeros((batch_size, 320, 280, 3), dtype=np.uint8)
image_files = ["dummy.png", "dumpy_2.pny"]
call = JsonOutput(**params)
json_output = call(predict, raw_images, image_files)
output = json.loads(json_output)
assert output["classes"] == [{"id": i, "name": name} for i, name in enumerate(classes)]
assert output["task"] == str(task.value)
results = output["results"]
assert [result["file_path"] for result in results] == image_files
for i in range(batch_size):
predictions = results[i]["prediction"]
for class_id in range(len(classes)):
mask = predictions[i]["mask"]
mask_data = base64.b64decode(mask)
mask_pil_image = PIL.Image.open(BytesIO(mask_data))
mask_image = np.array(mask_pil_image)
assert mask_image.shape == (320, 280)
def run_prediction(input_image, model, config_file, trial=1):
if not input_image or not model or not config_file:
logger.error('Please check usage with --help option')
exit(1)
config = load_yaml(config_file)
# load the image
image_data = load_image(input_image)
raw_image = image_data
# initialize Network
nn = _init(model, config)
pre_process = build_pre_process(config.PRE_PROCESSOR)
post_process = build_post_process(config.POST_PROCESSOR)
# call functions once to exclude the first result which include some initializations
init_output = _pre_process(image_data, pre_process, config.DATA_FORMAT)
init_output = _run(nn, init_output)
init_output = _post_process(init_output, post_process)
results_total = []
results_pre = []
results_run = []
results_post = []
for _ in range(trial):
# pre process for image
output, bench_pre = _timerfunc(
_pre_process, (image_data, pre_process, config.DATA_FORMAT))
# run the model to inference
output, bench_run = _timerfunc(_run, (nn, output))
# pre process for output
output, bench_post = _timerfunc(_post_process, (output, post_process))
results_total.append(bench_pre + bench_run + bench_post)
results_pre.append(bench_pre)
results_run.append(bench_run)
results_post.append(bench_post)
time_stat = {
"total": {
"mean": np.mean(results_total),
"std": np.std(results_total)
},
"pre": {
"mean": np.mean(results_pre),
"std": np.std(results_pre)
},
"post": {
"mean": np.mean(results_post),
"std": np.std(results_post)
},
"run": {
"mean": np.mean(results_run),
"std": np.std(results_run)
},
}
# json output
json_output = JsonOutput(
task=Tasks(config.TASK),
classes=config.CLASSES,
image_size=config.IMAGE_SIZE,
data_format=config.DATA_FORMAT,
bench=time_stat,
)
image_from_json = ImageFromJson(
task=Tasks(config.TASK),
classes=config.CLASSES,
image_size=config.IMAGE_SIZE,
)
output_dir = "output"
outputs = output
raw_images = [raw_image]
image_files = [input_image]
json_obj = json_output(outputs, raw_images, image_files)
_save_json(output_dir, json_obj)
filename_images = image_from_json(json_obj, raw_images, image_files)
_save_images(output_dir, filename_images)
logger.info("Benchmark avg result(sec) for {} trials".format(trial))
logger.info(time_stat)