e = s + 5
opt.weights = opt.weights[:s] + ('fold%d' % fold) + opt.weights[e:]
opt.fold = fold
if opt.h5:
testset = h5_dataset.H5Dataset(opt, split=2)
opt.num_workers = 0
else:
testset = datasets.Dataset(opt, 'test')
loader = DataLoader(testset,
batch_size=1,
shuffle=False,
num_workers=0)
model.load_weights(opt.weights)
model.cuda()
log, rf, rt = mAP(model, loader, args, 0)
rt['log'] = average_dictionary(rt['log'], r_keys)
copy_log(rt)
print(log)
rts.append(rt)
else:
log, _, avg = mAP(model, loader, args, 0)
avg['log'] = average_dictionary(avg['log'], r_keys)
copy_log(avg)
rts = [avg]
print(log)
def final_log(dicts, keys, title):
res = average_dictionary(dicts, keys, False, True)
args.score_threshold = opt.score_threshold
args.num_queries = -1
args.score_nms_overlap = opt.score_nms_overlap
args.overlap_threshold = 0.5
args.gpu = True
args.use_external_proposals = int(opt.external_proposals)
args.max_proposals = opt.max_proposals
args.rpn_nms_thresh = opt.test_rpn_nms_thresh
args.num_workers = 6
args.numpy = False
trainlog = ''
start = time.time()
loss_history, mAPs = [], []
if opt.eval_first_iteration:
log, rf, rt = mAP(model, valloader, args, it)
trainlog += log
if show:
print(log)
best_score = (rt.mAP_qbe_50 + rt.mAP_qbs_50) / 2
mAPs.append((it, [rt.mAP_qbe_50, rt.mAP_qbs_50]))
else:
best_score = 0.0
if opt.weights:
opt.save_id += '_pretrained'
if not os.path.exists('checkpoints/ctrlfnet_mini/'):
os.makedirs('checkpoints/ctrlfnet_mini/')