def validate(net, val_dataloader, epoch, save_change_map_dir, save_roc_dir):
net.eval()
cont_conv5_total, cont_fc_total, cont_embedding_total, num = 0.0, 0.0, 0.0, 0.0
metric_for_conditions = util.init_metric_for_class_for_cmu(1)
for batch_idx, batch in enumerate(val_dataloader):
inputs1, input2, targets, filename, height, width = batch
height, width, filename = height.numpy()[0], width.numpy(
)[0], filename[0]
inputs1, input2, targets = inputs1.cuda(), input2.cuda(), targets.cuda(
)
inputs1, inputs2, targets = Variable(inputs1, volatile=True), Variable(
input2, volatile=True), Variable(targets)
out_conv5, out_fc, out_embedding = net(inputs1, inputs2)
out_conv5_t0, out_conv5_t1 = out_conv5
out_fc_t0, out_fc_t1 = out_fc
out_embedding_t0, out_embedding_t1 = out_embedding
conv5_distance_map = single_layer_similar_heatmap_visual(
out_conv5_t0, out_conv5_t1, save_change_map_dir, epoch, filename,
'conv5', 'l2')
fc_distance_map = single_layer_similar_heatmap_visual(
out_fc_t0, out_fc_t1, save_change_map_dir, epoch, filename, 'fc',
'l2')
embedding_distance_map = single_layer_similar_heatmap_visual(
out_embedding_t0, out_embedding_t1, save_change_map_dir, epoch,
filename, 'embedding', 'l2')
cont_conv5 = mc.RMS_Contrast(conv5_distance_map)
cont_fc = mc.RMS_Contrast(fc_distance_map)
cont_embedding = mc.RMS_Contrast(embedding_distance_map)
cont_conv5_total += cont_conv5
cont_fc_total += cont_fc
cont_embedding_total += cont_embedding
num += 1
prob_change = embedding_distance_map[0][0]
gt = targets.data.cpu().numpy()
FN, FP, posNum, negNum = mc.eval_image_rewrite(gt[0],
prob_change,
cl_index=1)
metric_for_conditions[0]['total_fp'] += FP
metric_for_conditions[0]['total_fn'] += FN
metric_for_conditions[0]['total_posnum'] += posNum
metric_for_conditions[0]['total_negnum'] += negNum
cont_conv5_mean, cont_fc_mean,cont_embedding_mean = cont_conv5_total/num, \
cont_fc_total/num,cont_embedding_total/num
thresh = np.array(range(0, 256)) / 255.0
conds = metric_for_conditions.keys()
for cond_name in conds:
total_posnum = metric_for_conditions[cond_name]['total_posnum']
total_negnum = metric_for_conditions[cond_name]['total_negnum']
total_fn = metric_for_conditions[cond_name]['total_fn']
total_fp = metric_for_conditions[cond_name]['total_fp']
metric_dict = mc.pxEval_maximizeFMeasure(total_posnum,
total_negnum,
total_fn,
total_fp,
thresh=thresh)
metric_for_conditions[cond_name].setdefault('metric', metric_dict)
metric_for_conditions[cond_name].setdefault('contrast_conv5',
cont_conv5_mean)
metric_for_conditions[cond_name].setdefault('contrast_fc',
cont_fc_mean)
metric_for_conditions[cond_name].setdefault('contrast_embedding',
cont_embedding_mean)
f_score_total = 0.0
for cond_name in conds:
pr, recall, f_score = metric_for_conditions[cond_name]['metric'][
'precision'], metric_for_conditions[cond_name]['metric'][
'recall'], metric_for_conditions[cond_name]['metric']['MaxF']
roc_save_epoch_dir = os.path.join(save_roc_dir, str(epoch))
check_dir(roc_save_epoch_dir)
roc_save_epoch_cat_dir = os.path.join(roc_save_epoch_dir)
check_dir(roc_save_epoch_cat_dir)
mc.save_PTZ_metric2disk(metric_for_conditions[cond_name],
roc_save_epoch_cat_dir)
roc_save_dir = os.path.join(roc_save_epoch_cat_dir,
'_' + str(cond_name) + '_roc.png')
mc.plotPrecisionRecall(pr, recall, roc_save_dir, benchmark_pr=None)
f_score_total += f_score
print(f_score_total / (len(conds)))
return f_score_total / len(conds)
def validate(net, val_dataloader, epoch, save_change_map_dir, save_roc_dir):
net.eval()
cont_conv5_total, cont_fc_total, cont_embedding_total, num = 0.0, 0.0, 0.0, 0.0
metric_for_conditions = util.init_metric_for_class_for_cmu(1)
total_FP = 0.0
total_FN = 0.0
total_TP = 0.0
total_TN = 0.0
total_F1 = 0.0
num = 0.0
for batch_idx, batch in enumerate(val_dataloader):
inputs1, input2, targets, filename, height, width = batch
height, width, filename = height.numpy()[0], width.numpy(
)[0], filename[0]
inputs1, input2, targets = inputs1.cuda(), input2.cuda(), targets.cuda(
)
inputs1, inputs2, targets = Variable(inputs1, volatile=True), Variable(
input2, volatile=True), Variable(targets)
out_conv5, out_fc, out_embedding = net(inputs1, inputs2)
out_conv5_t0, out_conv5_t1 = out_conv5
out_fc_t0, out_fc_t1 = out_fc
out_embedding_t0, out_embedding_t1 = out_embedding
conv5_distance_map = single_layer_similar_heatmap_visual(
out_conv5_t0, out_conv5_t1, save_change_map_dir, epoch, filename,
'conv5', 'l2')
fc_distance_map = single_layer_similar_heatmap_visual(
out_fc_t0, out_fc_t1, save_change_map_dir, epoch, filename, 'fc',
'l2')
embedding_distance_map = single_layer_similar_heatmap_visual(
out_embedding_t0, out_embedding_t1, save_change_map_dir, epoch,
filename, 'embedding', 'l2')
prob_change = embedding_distance_map[0][0]
gt = targets.data.cpu().numpy()
#FN, FP, posNum, negNum = mc.eval_image_rewrite(gt[0], prob_change, cl_index=1)
FN, FP, TP, TN = mc.compute_FNFP(gt[0], prob_change)
Precision = TP / (TP + FP + 1e-10)
Recall = TP / (TP + FN + 1e-10)
F_score = 2 * Precision / (Precision + Recall + 1e-10)
OA = (TP + TN) / (TP + TN + FP + FN + 1e-10)
#print('Metirc in Batch:',batch_idx,'in Validation.','Precision:',Precision,'Recall:',Recall,'F1_socre',F_score,'OA:',OA)
total_FP = total_FP + FP
total_FN = total_FN + FN
total_TP = total_TP + TP
total_TN = total_TN + TN
num += 1
pr = total_TP / (total_TP + total_TN + 1e-10)
recall = total_TP / (total_TP + total_FN + 1e-10)
f_score = 2 * pr / (pr + recall)
oa = (total_TP + total_TN) / (total_TP + total_TN + total_TN + total_FN +
1e-10)
print('Metirc in Validation:', 'Precision:', pr, 'Recall:', recall,
'F1_socre', f_score, 'OA:', oa)
return f_score, pr, recall, oa