1 3 24 94

1 3 24 94

1 3 24 94

64 3 3 3

64 3 3 3

64 3 3 3

1

1

64 1 1 1

64 1 1 1

64 3 3 3 1 1 64 1 1 1 64 1 1 1

64 3 3 3

1 3 24 94 64 3 3 3

1 64 24 94

1 64 1 1

1 64 24 94 1 64 1 1

1 64 24 94

1 64 24 94

1 64 24 94

1 64 24 94

1 64 22 92

32 64 1 1

1 64 22 92 32 64 1 1

1 32 22 92

1 32 1 1

1 32 22 92 1 32 1 1

1 32 22 92

1 32 22 92

1 32 22 92

1 32 22 92

1 32 22 92

32 32 3 1

32 32 3 1

32 32 3 1

1

1

32 1 1 1

32 1 1 1

32 32 3 1 1 1 32 1 1 1 32 1 1 1

32 32 3 1

1 32 22 92 32 32 3 1

1 32 22 92

1 32 1 1

1 32 22 92 1 32 1 1

1 32 22 92

1 32 22 92

1 32 22 92

1 32 22 92

1 32 22 92

32 32 1 3

32 32 1 3

32 32 1 3

1

1

32 1 1 1

32 1 1 1

32 32 1 3 1 1 32 1 1 1 32 1 1 1

32 32 1 3

1 32 22 92 32 32 1 3

1 32 22 92

1 32 1 1

1 32 22 92 1 32 1 1

1 32 22 92

1 32 22 92

1 32 22 92

1 32 22 92

1 32 22 92

128 32 1 1

128 32 1 1

128 32 1 1

1

1

128 1 1 1

128 1 1 1

128 32 1 1 1 1 128 1 1 1 128 1 1 1

128 32 1 1

1 32 22 92 128 32 1 1

1 128 22 92

1 128 1 1

1 128 22 92 1 128 1 1

1 128 22 92

1 128 22 92

1 128 22 92

1 128 22 92

1 128 22 92

1 128 22 92

1 128 11 90

64 128 1 1

64 128 1 1

64 128 1 1

1

1

64 1 1 1

64 1 1 1

64 128 1 1 1 1 64 1 1 1 64 1 1 1

64 128 1 1

1 128 11 90 64 128 1 1

1 64 11 90

1 64 1 1

1 64 11 90 1 64 1 1

1 64 11 90

1 64 11 90

1 64 11 90

1 64 11 90

1 64 11 90

64 64 3 1

64 64 3 1

64 64 3 1

1

1

64 1 1 1

64 1 1 1

64 64 3 1 1 1 64 1 1 1 64 1 1 1

64 64 3 1

1 64 11 90 64 64 3 1

1 64 11 90

1 64 1 1

1 64 11 90 1 64 1 1

1 64 11 90

1 64 11 90

1 64 11 90

1 64 11 90

1 64 11 90

64 64 1 3

64 64 1 3

64 64 1 3

1

1

64 1 1 1

64 1 1 1

64 64 1 3 1 1 64 1 1 1 64 1 1 1

64 64 1 3

1 64 11 90 64 64 1 3

1 64 11 90

1 64 1 1

1 64 11 90 1 64 1 1

1 64 11 90

1 64 11 90

1 64 11 90

1 64 11 90

1 64 11 90

256 64 1 1

256 64 1 1

256 64 1 1

1

1

256 1 1 1

256 1 1 1

256 64 1 1 1 1 256 1 1 1 256 1 1 1

256 64 1 1

1 64 11 90 256 64 1 1

1 256 11 90

1 256 1 1

1 256 11 90 1 256 1 1

1 256 11 90

1 256 11 90

1 256 11 90

1 256 11 90

1 256 11 90

64 256 1 1

64 256 1 1

64 256 1 1

1

1

64 1 1 1

64 1 1 1

64 256 1 1 1 1 64 1 1 1 64 1 1 1

64 256 1 1

1 256 11 90 64 256 1 1

1 64 11 90

1 64 1 1

1 64 11 90 1 64 1 1

1 64 11 90

1 64 11 90

1 64 11 90

1 64 11 90

1 64 11 90

64 64 3 1

64 64 3 1

64 64 3 1

1

1

64 1 1 1

64 1 1 1

64 64 3 1 1 1 64 1 1 1 64 1 1 1

64 64 3 1

1 64 11 90 64 64 3 1

1 64 11 90

1 64 1 1

1 64 11 90 1 64 1 1

1 64 11 90

1 64 11 90

1 64 11 90

1 64 11 90

1 64 11 90

64 64 1 3

64 64 1 3

64 64 1 3

1

1

64 1 1 1

64 1 1 1

64 64 1 3 1 1 64 1 1 1 64 1 1 1

64 64 1 3

1 64 11 90 64 64 1 3

1 64 11 90

1 64 1 1

1 64 11 90 1 64 1 1

1 64 11 90

1 64 11 90

1 64 11 90

1 64 11 90

1 64 11 90

256 64 1 1

256 64 1 1

256 64 1 1

1

1

256 1 1 1

256 1 1 1

256 64 1 1 1 1 256 1 1 1 256 1 1 1

256 64 1 1

1 64 11 90 256 64 1 1

1 256 11 90

1 256 1 1

1 256 11 90 1 256 1 1

1 256 11 90

1 256 11 90

1 256 11 90

1 256 11 90

1 256 11 90

1 256 11 90

1 256 5 88

128 256 5 1

128 256 5 1

128 256 5 1

1

1

128 1 1 1

128 1 1 1

128 256 5 1 1 1 128 1 1 1 128 1 1 1

128 256 5 1

1 256 5 88 128 256 5 1

1 128 1 88

1 128 1 1

1 128 1 88 1 128 1 1

1 128 1 88

1 128 1 88

1 128 1 88

1 128 1 88

1 128 1 88

71 128 1 13

71 128 1 13

71 128 1 13

1

1

71 1 1 1

71 1 1 1

71 128 1 13 1 1 71 1 1 1 71 1 1 1

71 128 1 13

1 128 1 88 71 128 1 13

1 71 1 88

1 71 1 1

1 71 1 88 1 71 1 1

1 71 1 88

1 71 1 88

1 71 1 88

1

128 6248

128 6248

2

1

2 1

1

1 1

2

1 71 1 88 2

1 6248

1 6248 128 6248

1 128

1 128

1 128 1 128

1 128

4

1 128 4

1 128 1 1

4

1 128 1 1 4

1 128 1 88

1 71 1 88 1 128 1 88

1 199 1 88

71 199 1 1

1 199 1 88 71 199 1 1

1 71 1 88

1 71 1 1

1 71 1 88 1 71 1 1

1 71 1 88

4

1 71 1 88 4

88 1 71 1

3

88 1 71 1 3

88 1 71

88 1

88 1 71 88 1

1 88 1 1

1 88 1 1

{ 'compression': { 'algorithms': [ { 'name': 'AccuracyAwareQuantization', 'params': { 'drop_type': 'relative', 'max_iter_num': 20, 'maximal_drop': 0.01, 'metric_subset_ratio': 0.2, 'preset': 'performance', 'stat_subset_size': 300, 'tune_hyperparams': true } } ], 'target_device': 'CPU' }, 'engine': { 'models': [ { 'name': 'license-plate-recognition-barrier-0001', 'launchers': [ { 'framework': 'dlsdk', 'adapter': 'lpr', 'inputs': [ { 'name': 'seq_ind', 'type': 'CONST_INPUT', 'value': [ [ 0 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ], [ 1 ] ] } ], 'device': 'CPU' } ], 'datasets': [ { 'name': 'synthetic_chinese_license_plates', 'data_source': 'PATH', 'annotation_conversion': { 'converter': 'lpr_json', 'annotation_file': 'PATH', 'decoding_dictionary_file': 'PATH' }, 'annotation': 'lpr.pickle', 'dataset_meta': 'lpr.json', 'preprocessing': [ { 'type': 'crop_rect' }, { 'type': 'resize', 'dst_width': 94, 'dst_height': 24 } ], 'metrics': [ { 'type': 'character_recognition_accuracy' } ] } ] } ], 'stat_requests_number': null, 'eval_requests_number': null, 'type': 'accuracy_checker' } }