def FasterRcnn_eval(dataset_path, ckpt_path, ann_file):
"""FasterRcnn evaluation."""
ds = create_fasterrcnn_dataset(dataset_path, batch_size=config.test_batch_size, is_training=False)
net = Faster_Rcnn_Resnet50(config)
param_dict = load_checkpoint(ckpt_path)
load_param_into_net(net, param_dict)
net.set_train(False)
eval_iter = 0
total = ds.get_dataset_size()
outputs = []
dataset_coco = COCO(ann_file)
print("\n========================================\n")
print("total images num: ", total)
print("Processing, please wait a moment.")
max_num = 128
for data in ds.create_dict_iterator(num_epochs=1):
eval_iter = eval_iter + 1
img_data = data['image']
img_metas = data['image_shape']
gt_bboxes = data['box']
gt_labels = data['label']
gt_num = data['valid_num']
start = time.time()
# run net
output = net(img_data, img_metas, gt_bboxes, gt_labels, gt_num)
end = time.time()
print("Iter {} cost time {}".format(eval_iter, end - start))
# output
all_bbox = output[0]
all_label = output[1]
all_mask = output[2]
for j in range(config.test_batch_size):
all_bbox_squee = np.squeeze(all_bbox.asnumpy()[j, :, :])
all_label_squee = np.squeeze(all_label.asnumpy()[j, :, :])
all_mask_squee = np.squeeze(all_mask.asnumpy()[j, :, :])
all_bboxes_tmp_mask = all_bbox_squee[all_mask_squee, :]
all_labels_tmp_mask = all_label_squee[all_mask_squee]
if all_bboxes_tmp_mask.shape[0] > max_num:
inds = np.argsort(-all_bboxes_tmp_mask[:, -1])
inds = inds[:max_num]
all_bboxes_tmp_mask = all_bboxes_tmp_mask[inds]
all_labels_tmp_mask = all_labels_tmp_mask[inds]
outputs_tmp = bbox2result_1image(all_bboxes_tmp_mask, all_labels_tmp_mask, config.num_classes)
outputs.append(outputs_tmp)
eval_types = ["bbox"]
result_files = results2json(dataset_coco, outputs, "./results.pkl")
coco_eval(result_files, eval_types, dataset_coco, single_result=True)
def get_eval_result(ann_file, img_path):
""" Get metrics result according to the annotation file and result file"""
max_num = 128
result_path = "./result_Files/"
outputs = []
dataset_coco = COCO(ann_file)
img_ids = dataset_coco.getImgIds()
for img_id in img_ids:
file_id = str(img_id).zfill(12)
file = img_path + "/" + file_id + ".jpg"
img_size = get_img_size(file)
resize_ratio = get_resize_ratio(img_size)
img_metas = np.array([img_size[1], img_size[0]] +
[resize_ratio, resize_ratio])
bbox_result_file = result_path + file_id + "_0.bin"
label_result_file = result_path + file_id + "_1.bin"
mask_result_file = result_path + file_id + "_2.bin"
mask_fb_result_file = result_path + file_id + "_3.bin"
all_bbox = np.fromfile(bbox_result_file,
dtype=np.float16).reshape(80000, 5)
all_label = np.fromfile(label_result_file,
dtype=np.int32).reshape(80000, 1)
all_mask = np.fromfile(mask_result_file,
dtype=np.bool_).reshape(80000, 1)
all_mask_fb = np.fromfile(mask_fb_result_file,
dtype=np.float16).reshape(80000, 28, 28)
all_bbox_squee = np.squeeze(all_bbox)
all_label_squee = np.squeeze(all_label)
all_mask_squee = np.squeeze(all_mask)
all_mask_fb_squee = np.squeeze(all_mask_fb)
all_bboxes_tmp_mask = all_bbox_squee[all_mask_squee, :]
all_labels_tmp_mask = all_label_squee[all_mask_squee]
all_mask_fb_tmp_mask = all_mask_fb_squee[all_mask_squee, :, :]
if all_bboxes_tmp_mask.shape[0] > max_num:
inds = np.argsort(-all_bboxes_tmp_mask[:, -1])
inds = inds[:max_num]
all_bboxes_tmp_mask = all_bboxes_tmp_mask[inds]
all_labels_tmp_mask = all_labels_tmp_mask[inds]
all_mask_fb_tmp_mask = all_mask_fb_tmp_mask[inds]
bbox_results = bbox2result_1image(all_bboxes_tmp_mask,
all_labels_tmp_mask,
config.num_classes)
segm_results = get_seg_masks(all_mask_fb_tmp_mask, all_bboxes_tmp_mask,
all_labels_tmp_mask, img_metas, True,
config.num_classes)
outputs.append((bbox_results, segm_results))
eval_types = ["bbox", "segm"]
result_files = results2json(dataset_coco, outputs, "./results.pkl")
coco_eval(result_files, eval_types, dataset_coco, single_result=False)
def get_eval_result(ann_file, result_path):
""" get evaluation result of faster rcnn"""
max_num = 128
result_path = result_path
outputs = []
dataset_coco = COCO(ann_file)
img_ids = dataset_coco.getImgIds()
for img_id in img_ids:
file_id = str(img_id).zfill(12)
bbox_result_file = os.path.join(result_path, file_id + "_0.bin")
label_result_file = os.path.join(result_path, file_id + "_1.bin")
mask_result_file = os.path.join(result_path, file_id + "_2.bin")
all_bbox = np.fromfile(bbox_result_file,
dtype=np.float16).reshape(80000, 5)
all_label = np.fromfile(label_result_file,
dtype=np.int32).reshape(80000, 1)
all_mask = np.fromfile(mask_result_file,
dtype=np.bool_).reshape(80000, 1)
all_bbox_squee = np.squeeze(all_bbox)
all_label_squee = np.squeeze(all_label)
all_mask_squee = np.squeeze(all_mask)
all_bboxes_tmp_mask = all_bbox_squee[all_mask_squee, :]
all_labels_tmp_mask = all_label_squee[all_mask_squee]
if all_bboxes_tmp_mask.shape[0] > max_num:
inds = np.argsort(-all_bboxes_tmp_mask[:, -1])
inds = inds[:max_num]
all_bboxes_tmp_mask = all_bboxes_tmp_mask[inds]
all_labels_tmp_mask = all_labels_tmp_mask[inds]
outputs_tmp = bbox2result_1image(all_bboxes_tmp_mask,
all_labels_tmp_mask,
config.num_classes)
outputs.append(outputs_tmp)
eval_types = ["bbox"]
result_files = results2json(dataset_coco, outputs, "./results.pkl")
coco_eval(result_files, eval_types, dataset_coco, single_result=False)
