def test_fastrcnnpy_grocery_training(device_id):
if cntk_device(device_id).type() != DeviceKind_GPU:
pytest.skip('test only runs on GPU') # it runs very slow in CPU
try_set_default_device(cntk_device(device_id))
from utils.config_helpers import merge_configs
from FastRCNN_config import cfg as detector_cfg
from utils.configs.AlexNet_config import cfg as network_cfg
from utils.configs.Grocery_config import cfg as dataset_cfg
cfg = merge_configs([detector_cfg, network_cfg, dataset_cfg])
cfg["CNTK"].FORCE_DETERMINISTIC = True
cfg["CNTK"].DEBUG_OUTPUT = False
cfg["CNTK"].MAKE_MODE = False
cfg["CNTK"].FAST_MODE = False
cfg["CNTK"].MAX_EPOCHS = 4
cfg.IMAGE_WIDTH = 600
cfg.IMAGE_HEIGHT = 600
cfg.NUM_ROI_PROPOSALS = 200
cfg.USE_GPU_NMS = False
cfg.VISUALIZE_RESULTS = False
cfg["DATA"].MAP_FILE_PATH = grocery_path
externalData = 'CNTK_EXTERNAL_TESTDATA_SOURCE_DIRECTORY' in os.environ
if externalData:
extPath = os.environ['CNTK_EXTERNAL_TESTDATA_SOURCE_DIRECTORY']
cfg['BASE_MODEL_PATH'] = os.path.join(extPath, "PreTrainedModels",
"AlexNet", "v1",
"AlexNet_ImageNet_Caffe.model")
else:
cfg['BASE_MODEL_PATH'] = os.path.join(
abs_path,
*"../../../../PretrainedModels/AlexNet_ImageNet_Caffe.model".split(
"/"))
from FastRCNN_train import prepare, train_fast_rcnn
from FastRCNN_eval import compute_test_set_aps
prepare(cfg, False)
np.random.seed(seed=3)
trained_model = train_fast_rcnn(cfg)
eval_results = compute_test_set_aps(trained_model, cfg)
meanAP = np.nanmean(list(eval_results.values()))
print('meanAP={}'.format(meanAP))
assert meanAP > 0.01
def test_fastrcnnpy_grocery_training(device_id):
if cntk_device(device_id).type() != DeviceKind_GPU:
pytest.skip('test only runs on GPU') # it runs very slow in CPU
try_set_default_device(cntk_device(device_id))
from utils.config_helpers import merge_configs
from FastRCNN_config import cfg as detector_cfg
from utils.configs.AlexNet_config import cfg as network_cfg
from utils.configs.Grocery_config import cfg as dataset_cfg
cfg = merge_configs([detector_cfg, network_cfg, dataset_cfg])
cfg["CNTK"].FORCE_DETERMINISTIC = True
cfg["CNTK"].DEBUG_OUTPUT = False
cfg["CNTK"].MAKE_MODE = False
cfg["CNTK"].FAST_MODE = False
cfg["CNTK"].MAX_EPOCHS = 4
cfg.IMAGE_WIDTH = 600
cfg.IMAGE_HEIGHT = 600
cfg.NUM_ROI_PROPOSALS = 200
cfg.USE_GPU_NMS = False
cfg.VISUALIZE_RESULTS = False
cfg["DATA"].MAP_FILE_PATH = grocery_path
externalData = 'CNTK_EXTERNAL_TESTDATA_SOURCE_DIRECTORY' in os.environ
if externalData:
extPath = os.environ['CNTK_EXTERNAL_TESTDATA_SOURCE_DIRECTORY']
cfg['BASE_MODEL_PATH'] = os.path.join(extPath, "PreTrainedModels", "AlexNet", "v1", "AlexNet_ImageNet_Caffe.model")
else:
cfg['BASE_MODEL_PATH'] = os.path.join(abs_path, *"../../../../PretrainedModels/AlexNet_ImageNet_Caffe.model".split("/"))
from FastRCNN_train import prepare, train_fast_rcnn
from FastRCNN_eval import compute_test_set_aps
prepare(cfg, False)
np.random.seed(seed=3)
trained_model = train_fast_rcnn(cfg)
eval_results = compute_test_set_aps(trained_model, cfg)
meanAP = np.nanmean(list(eval_results.values()))
print('meanAP={}'.format(meanAP))
assert meanAP > 0.01
# load configs for detector, base network and data set
from FastRCNN_config import cfg as detector_cfg
# for VGG16 base model use: from utils.configs.VGG16_config import cfg as network_cfg
# for AlexNet base model use: from utils.configs.AlexNet_config import cfg as network_cfg
from utils.configs.AlexNet_config import cfg as network_cfg
# for Pascal VOC 2007 data set use: from utils.configs.Pascal_config import cfg as dataset_cfg
# for the Grocery data set use: from utils.configs.Grocery_config import cfg as dataset_cfg
from utils.configs.Prometheus_config import cfg as dataset_cfg
return merge_configs([detector_cfg, network_cfg, dataset_cfg])
# trains and evaluates a Fast R-CNN model.
if __name__ == '__main__':
cfg = get_configuration()
prepare(cfg, True)
# train and test
trained_model = train_fast_rcnn(cfg)
eval_results = compute_test_set_aps(trained_model, cfg)
# write AP results to output
for class_name in eval_results:
print('AP for {:>15} = {:.4f}'.format(class_name,
eval_results[class_name]))
print('Mean AP = {:.4f}'.format(np.nanmean(list(eval_results.values()))))
# Plot results on test set images
if cfg.VISUALIZE_RESULTS:
num_eval = min(cfg["DATA"].NUM_TEST_IMAGES, 100)
results_folder = os.path.join(cfg.OUTPUT_PATH, cfg["DATA"].DATASET)
def get_configuration():
# load configs for detector, base network and data set
from FastRCNN_config import cfg as detector_cfg
# for VGG16 base model use: from utils.configs.VGG16_config import cfg as network_cfg
# for AlexNet base model use: from utils.configs.AlexNet_config import cfg as network_cfg
from utils.configs.AlexNet_config import cfg as network_cfg
# for Pascal VOC 2007 data set use: from utils.configs.Pascal_config import cfg as dataset_cfg
# for the Grocery data set use: from utils.configs.Grocery_config import cfg as dataset_cfg
from utils.configs.Grocery_config import cfg as dataset_cfg
return merge_configs([detector_cfg, network_cfg, dataset_cfg])
# trains and evaluates a Fast R-CNN model.
if __name__ == '__main__':
cfg = get_configuration()
prepare(cfg, True)
# train and test
trained_model = train_fast_rcnn(cfg)
eval_results = compute_test_set_aps(trained_model, cfg)
# write AP results to output
for class_name in eval_results: print('AP for {:>15} = {:.4f}'.format(class_name, eval_results[class_name]))
print('Mean AP = {:.4f}'.format(np.nanmean(list(eval_results.values()))))
# Plot results on test set images
if cfg.VISUALIZE_RESULTS:
num_eval = min(cfg["DATA"].NUM_TEST_IMAGES, 100)
results_folder = os.path.join(cfg.OUTPUT_PATH, cfg["DATA"].DATASET)
evaluator = FastRCNN_Evaluator(trained_model, cfg)
plot_test_set_results(evaluator, num_eval, results_folder, cfg)