def mini_eval(self, current_step):
if current_step % self.config.TRAIN.mini_eval_step != 0:
return
temp_meter_rec = AverageMeter()
temp_meter_pred = AverageMeter()
self.STAE.eval()
for data in self.val_dataloader:
# get the reconstruction and prediction video clip
time_len = data.shape[2]
rec_time = time_len // 2
inupt_rec_mini = data[:, :,
0:rec_time, :, :].cuda() # 0 ~ t//2 frame
input_pred_mini = data[:, :, rec_time:time_len, :, :].cuda(
) # t//2 ~ t frame
# Use the model, get the output
output_rec_mini, output_pred_mini = self.STAE(inupt_rec_mini)
rec_psnr_mini = psnr_error(output_rec_mini.detach(),
inupt_rec_mini)
pred_psnr_mini = psnr_error(output_pred_mini.detach(),
input_pred_mini)
temp_meter_rec.update(rec_psnr_mini.detach())
temp_meter_pred.update(pred_psnr_mini.detach())
self.logger.info(
f'&^*_*^& ==> Step:{current_step}/{self.max_steps} the rec PSNR is {temp_meter_rec.avg:.3f}, the pred PSNR is {temp_meter_pred.avg:.3f}'
)
def mini_eval(self, current_step):
if current_step % self.config.TRAIN.mini_eval_step != 0:
return
temp_meter_frame = AverageMeter()
temp_meter_flow = AverageMeter()
self.G.eval()
self.D.eval()
for data in self.val_dataloader:
# get the data
target_mini = data[:, :, 1, :, :]
input_data_mini = data[:, :, 0, :, :]
# squeeze the dimension
target_mini = target_mini.view(target_mini.shape[0], -1,
target_mini.shape[-2],
target_mini.shape[-1]).cuda()
input_data_mini = input_data_mini.view(
input_data_mini.shape[0], -1, input_data_mini.shape[-2],
input_data_mini.shape[-1]).cuda()
# Use the model, get the output
output_flow_G_mini, output_frame_G_mini = self.G(input_data_mini)
input_gtFlowEstimTensor = torch.cat([input_data_mini, target_mini],
1)
gtFlow, _ = flow_batch_estimate(self.F, input_gtFlowEstimTensor)
frame_psnr_mini = psnr_error(output_frame_G_mini.detach(),
target_mini)
flow_psnr_mini = psnr_error(output_flow_G_mini.detach(), gtFlow)
temp_meter_frame.update(frame_psnr_mini.detach())
temp_meter_flow.update(flow_psnr_mini.detach())
self.logger.info(
f'&^*_*^& ==> Step:{current_step}/{self.max_steps} the frame PSNR is {temp_meter_frame.avg:.3f}, the flow PSNR is {temp_meter_flow.avg:.3f}'
)
def mini_eval(self, current_step):
if current_step % self.config.TRAIN.mini_eval_step != 0:
return
temp_meter_A = AverageMeter()
temp_meter_B = AverageMeter()
temp_meter_C = AverageMeter()
self.A.eval()
self.B.eval()
self.C.eval()
self.Detector.eval()
for data in self.val_dataloader:
# base on the D to get each frame
# in this method, D = 3 and not change
future_mini = data[:, -1, :, :, :].cuda() # t+1 frame
current_mini = data[:, 1, :, :, :].cuda() # t frame
past_mini = data[:, 0, :, :, :].cuda() # t-1 frame
bboxs_mini = get_batch_dets(self.Detector, current_mini)
for index, bbox in enumerate(bboxs_mini):
if bbox.numel() == 0:
bbox = bbox.new_zeros([1, 4])
# get the crop objects
input_currentObject_B, _ = multi_obj_grid_crop(
current_mini[index], bbox)
future_object, _ = multi_obj_grid_crop(future_mini[index],
bbox)
future2current = torch.stack(
[future_object, input_currentObject_B], dim=1)
past_object, _ = multi_obj_grid_crop(past_mini[index], bbox)
current2past = torch.stack(
[input_currentObject_B, past_object], dim=1)
_, _, input_objectGradient_A = frame_gradient(future2current)
input_objectGradient_A = input_objectGradient_A.sum(1)
_, _, input_objectGradient_C = frame_gradient(current2past)
input_objectGradient_C = input_objectGradient_A.sum(1)
_, output_recGradient_A = self.A(input_objectGradient_A)
_, output_recObject_B = self.B(input_currentObject_B)
_, output_recGradient_C = self.C(input_objectGradient_C)
psnr_A = psnr_error(output_recGradient_A.detach(),
input_objectGradient_A)
psnr_B = psnr_error(output_recObject_B.detach(),
input_currentObject_B)
psnr_C = psnr_error(output_recGradient_C.detach(),
input_objectGradient_C)
temp_meter_A.update(psnr_A.detach())
temp_meter_B.update(psnr_B.detach())
temp_meter_C.update(psnr_C.detach())
self.logger.info(
f'&^*_*^& ==> Step:{current_step}/{self.max_steps} the A PSNR is {temp_meter_A.avg:.2f}, the B PSNR is {temp_meter_B.avg:.2f}, the C PSNR is {temp_meter_C.avg:.2f}'
)
def mini_eval(self, current_step):
if current_step % 10 != 0 or current_step == 0:
return
temp_meter_frame = AverageMeter()
temp_meter_flow = AverageMeter()
self.G.eval()
self.D.eval()
for data in self.val_dataloader:
# base on the D to get each frame
target_mini = data[:, :, -1, :, :].cuda() # t+1 frame
input_data = data[:, :, :-1, :, :] # 0 ~ t frame
input_last_mini = input_data[:, :, -1, :, :].cuda() # t frame
# squeeze the D dimension to C dimension, shape comes to [N, C, H, W]
input_data_mini = input_data.view(input_data.shape[0], -1, input_data.shape[-2], input_data.shape[-1]).cuda()
output_pred_G = self.G(input_data_mini)
gtFlow, _ = flow_batch_estimate(self.F, torch.cat([input_last_mini, target_mini], 1))
predFlow, _ = flow_batch_estimate(self.F, torch.cat([input_last_mini, output_pred_G], 1))
frame_psnr_mini = psnr_error(output_pred_G.detach(), target_mini)
flow_psnr_mini = psnr_error(predFlow, gtFlow)
temp_meter_frame.update(frame_psnr_mini.detach())
temp_meter_flow.update(flow_psnr_mini.detach())
self.logger.info(f'&^*_*^& ==> Step:{current_step}/{self.max_steps} the PSNR is {temp_meter_frame.avg:.2f}, the flow PSNR is {temp_meter_flow.avg:.2f}')
def mini_eval(self, current_step):
if current_step % self.config.TRAIN.mini_eval_step != 0:
return
temp_meter_frame = AverageMeter()
self.MemAE.eval()
for data in self.val_dataloader:
# get the data
input_data_mini = data.cuda()
output_rec, _ = self.MemAE(input_data_mini)
frame_psnr_mini = psnr_error(output_rec.detach(), input_data_mini)
temp_meter_frame.update(frame_psnr_mini.detach())
self.logger.info(
f'&^*_*^& ==> Step:{current_step}/{self.max_steps} the frame PSNR is {temp_meter_frame.avg:.3f}'
)
def evaluate(self, current_step):
'''
Evaluate the results of the model
!!! Will change, e.g. accuracy, mAP.....
!!! Or can call other methods written by the official
'''
tb_writer = self.trainer.kwargs['writer_dict']['writer']
global_steps = self.trainer.kwargs['writer_dict']['global_steps_{}'.format(self.trainer.kwargs['model_type'])]
frame_num = self.config.DATASET.test_clip_length
psnr_records=[]
score_records=[]
total = 0
# for dirs in video_dirs:
random_video_sn = torch.randint(0, len(self.trainer.test_dataset_keys), (1,))
for sn, video_name in enumerate(self.trainer.test_dataset_keys):
# _temp_test_folder = os.path.join(self.testing_data_folder, dir)
# need to improve
# dataset = AvenueTestOld(_temp_test_folder, clip_length=frame_num)
dataset = self.trainer.test_dataset_dict[video_name]
len_dataset = dataset.pics_len
test_iters = len_dataset - frame_num + 1
test_counter = 0
data_loader = DataLoader(dataset=dataset, batch_size=1, shuffle=False, num_workers=1)
# import ipdb; ipdb.set_trace()
psnrs = np.empty(shape=(len_dataset,),dtype=np.float32)
scores = np.empty(shape=(len_dataset,),dtype=np.float32)
# for test_input, _ in data_loader:
vis_range = range(int(len_dataset*0.5), int(len_dataset*0.5 + 5))
for frame_sn, test_input in enumerate(data_loader):
test_target = test_input[:, -1].cuda()
test_input = test_input[:, :-1].transpose_(1,2).cuda()
g_output = self.trainer.G(test_input, test_target)
test_psnr = psnr_error(g_output, test_target)
test_psnr = test_psnr.tolist()
psnrs[test_counter+frame_num-1]=test_psnr
scores[test_counter+frame_num-1]=test_psnr
if sn == random_video_sn and (frame_sn in vis_range):
self.add_images(test_target, g_output, tb_writer, global_steps)
test_counter += 1
total+=1
if test_counter >= test_iters:
psnrs[:frame_num-1]=psnrs[frame_num-1]
scores[:frame_num-1]=(scores[frame_num-1],)
smax = max(scores)
smin = min(scores)
normal_scores = np.array([np.divide(s-smin, smax-smin) for s in scores])
psnr_records.append(psnrs)
score_records.append(normal_scores)
print(f'finish test video set {video_name}')
break
result_dict = {'dataset': self.trainer.config.DATASET.name, 'psnr': psnr_records, 'flow': [], 'names': [], 'diff_mask': [], 'score':score_records, 'num_vides':len(psnr_records)}
result_path = os.path.join(self.trainer.config.TEST.result_output, f'{self.trainer.verbose}_cfg#{self.trainer.config_name}@{self.trainer.kwargs["time_stamp"]}_results.pkl')
with open(result_path, 'wb') as writer:
pickle.dump(result_dict, writer, pickle.HIGHEST_PROTOCOL)
# results = eval_api.evaluate('compute_auc_score', result_path, self.trainer.logger, self.trainer.config)
results = self.trainer.evaluate_function(result_path, self.trainer.logger, self.trainer.config)
self.trainer.logger.info(results)
tb_writer.add_text('anopcn: AUC of ROC curve', f'auc is {results.auc}',global_steps)
return results.auc
def evaluate(self, current_step):
'''
Evaluate the results of the model
!!! Will change, e.g. accuracy, mAP.....
!!! Or can call other methods written by the official
'''
tb_writer = self.trainer.kwargs['writer_dict']['writer']
global_steps = self.trainer.kwargs['writer_dict'][
'global_steps_{}'.format(self.trainer.kwargs['model_type'])]
frame_num = self.trainer.config.DATASET.test_clip_length
psnr_records = []
score_records = []
# score_records_w=[]
w_dict = OrderedDict()
# total = 0
# calc the scores for the training set
for video_name in self.trainer.test_dataset_keys_w:
dataset = self.trainer.test_dataset_dict_w[video_name]
len_dataset = dataset.pics_len
test_iters = len_dataset - frame_num + 1
test_counter = 0
data_loader = DataLoader(dataset=dataset,
batch_size=1,
shuffle=False,
num_workers=1)
scores = [0.0 for i in range(len_dataset)]
for test_input in data_loader:
# import ipdb; ipdb.set_trace()
test_target = test_input[:, -1].cuda()
test_input = test_input[:, :-1].view(
test_input.shape[0], -1, test_input.shape[-2],
test_input.shape[-1]).cuda()
# import ipdb; ipdb.set_trace()
g_output_flow, g_output_frame = self.trainer.G(test_input)
gt_flow_esti_tensor = torch.cat([test_input, test_target], 1)
# flow_gt, _ = self.trainer.batch_estimate(gt_flow_esti_tensor)
flow_gt, _ = flow_batch_estimate(self.trainer.F,
gt_flow_esti_tensor)
# score = amc_score(test_input, g_output_frame, flow_gt, g_output_flow)
diff_appe, diff_flow = simple_diff(test_input, g_output_frame,
flow_gt, g_output_flow)
max_patch_appe, max_patch_flow = find_max_patch(
diff_appe, diff_flow)
score_appe = torch.mean(max_patch_appe)
score_flow = torch.mean(max_patch_flow)
scores[test_counter + frame_num - 1] = [score_appe, score_flow]
test_counter += 1
if test_counter >= test_iters:
scores[:frame_num - 1] = [scores[frame_num - 1]]
scores = torch.tensor(scores)
frame_w = torch.mean(scores[:, 0])
flow_w = torch.mean(scores[:, 1])
w_dict[video_name] = [len_dataset, frame_w, flow_w]
print(
f'finish calc the scores of training set {video_name} in step:{current_step}'
)
break
wf, wi = calc_w(w_dict)
# wf , wi = 1.0, 1.0
tb_writer.add_text('weight of train set',
f'w_f:{wf:.3f}, w_i:{wi:.3f}', global_steps)
num_videos = 0
random_video_sn = torch.randint(0, len(self.trainer.test_dataset_keys),
(1, ))
# calc the score for the test dataset
for sn, video_name in enumerate(self.trainer.test_dataset_keys):
num_videos += 1
# need to improve
dataset = self.trainer.test_dataset_dict[video_name]
len_dataset = dataset.pics_len
test_iters = len_dataset - frame_num + 1
test_counter = 0
data_loader = DataLoader(dataset=dataset,
batch_size=1,
shuffle=False,
num_workers=1)
vis_range = range(int(len_dataset * 0.5),
int(len_dataset * 0.5 + 5))
psnrs = np.empty(shape=(len_dataset, ), dtype=np.float32)
scores = np.empty(shape=(len_dataset, ), dtype=np.float32)
# scores = [0.0 for i in range(len_dataset)]
for frame_sn, test_input in enumerate(data_loader):
test_target = test_input[:, -1].cuda()
test_input = test_input[:, :-1].view(
test_input.shape[0], -1, test_input.shape[-2],
test_input.shape[-1]).cuda()
g_output_flow, g_output_frame = self.trainer.G(test_input)
gt_flow_esti_tensor = torch.cat([test_input, test_target], 1)
# flow_gt,_ = self.trainer.batch_estimate(gt_flow_esti_tensor)
flow_gt, _ = flow_batch_estimate(self.trainer.F,
gt_flow_esti_tensor)
# score = amc_score(test_input, g_output_frame, flow_gt, g_output_flow)
test_psnr = psnr_error(g_output_frame, test_target)
score = amc_score(test_input, g_output_frame, flow_gt,
g_output_flow, wf, wi)
# import ipdb; ipdb.set_trace()
test_psnr = test_psnr.tolist()
score = score.tolist()
psnrs[test_counter + frame_num - 1] = test_psnr
scores[test_counter + frame_num - 1] = score
test_counter += 1
if sn == random_video_sn and (frame_sn in vis_range):
self.add_images(test_target, flow_gt, g_output_frame,
g_output_flow, tb_writer, global_steps)
if test_counter >= test_iters:
psnrs[:frame_num - 1] = psnrs[frame_num - 1]
# import ipdb; ipdb.set_trace()
scores[:frame_num - 1] = (
scores[frame_num - 1],
) # fix the bug: TypeError: can only assign an iterable
smax = max(scores)
normal_scores = np.array(
[np.divide(s, smax) for s in scores])
psnr_records.append(psnrs)
score_records.append(normal_scores)
print(f'finish test video set {video_name}')
break
result_dict = {
'dataset': self.trainer.config.DATASET.name,
'psnr': psnr_records,
'flow': [],
'names': [],
'diff_mask': [],
'score': score_records,
'num_videos': num_videos
}
result_path = os.path.join(
self.trainer.config.TEST.result_output,
f'{self.trainer.verbose}_cfg#{self.trainer.config_name}#step{current_step}@{self.trainer.kwargs["time_stamp"]}_results.pkl'
)
with open(result_path, 'wb') as writer:
pickle.dump(result_dict, writer, pickle.HIGHEST_PROTOCOL)
# results = eval_api.evaluate('compute_auc_score', result_path, self.trainer.logger, self.trainer.config)
results = self.trainer.evaluate_function(
result_path, self.trainer.logger, self.trainer.config,
self.trainer.config.DATASET.score_type)
self.trainer.logger.info(results)
tb_writer.add_text('amc: AUC of ROC curve', f'auc is {results.auc}',
global_steps)
return results.auc
