RickZLLiao
commented
6 years ago My Config was as follow:
SSD with Mobilenet v1, configured for Oxford-IIIT Pets Dataset.
Users should configure the fine_tune_checkpoint field in the train config as
well as the label_map_path and input_path fields in the train_input_reader and
eval_input_reader. Search for "PATH_TO_BE_CONFIGURED" to find the fields that
should be configured.
model { ssd { num_classes: 1 box_coder { faster_rcnn_box_coder { y_scale: 10.0 x_scale: 10.0 height_scale: 5.0 width_scale: 5.0 } } matcher { argmax_matcher { matched_threshold: 0.5 unmatched_threshold: 0.5 ignore_thresholds: false negatives_lower_than_unmatched: true force_match_for_each_row: true } } similarity_calculator { iou_similarity { } } anchor_generator { ssd_anchor_generator { num_layers: 6 min_scale: 0.2 max_scale: 0.95 aspect_ratios: 1.0 aspect_ratios: 2.0 aspect_ratios: 0.5 aspect_ratios: 3.0 aspect_ratios: 0.3333 } } image_resizer { fixed_shape_resizer { height: 256 width: 256 } } box_predictor { convolutional_box_predictor { min_depth: 0 max_depth: 0 num_layers_before_predictor: 0 use_dropout: false dropout_keep_probability: 0.8 kernel_size: 1 box_code_size: 4 apply_sigmoid_to_scores: false conv_hyperparams { activation: RELU_6, regularizer { l2_regularizer { weight: 0.00004 } } initializer { truncated_normal_initializer { stddev: 0.03 mean: 0.0 } } batch_norm { train: true, scale: true, center: true, decay: 0.9997, epsilon: 0.001, } } } } feature_extractor { type: 'ssd_mobilenet_v1' min_depth: 16 depth_multiplier: 0.125 conv_hyperparams { activation: RELU_6, regularizer { l2_regularizer { weight: 0.00004 } } initializer { truncated_normal_initializer { stddev: 0.03 mean: 0.0 } } batch_norm { train: true, scale: true, center: true, decay: 0.9997, epsilon: 0.001, } } } loss { classification_loss { weighted_sigmoid { } } localization_loss { weighted_smooth_l1 { } } hard_example_miner { num_hard_examples: 3000 iou_threshold: 0.99 loss_type: CLASSIFICATION max_negatives_per_positive: 3 min_negatives_per_image: 0 } classification_weight: 1.0 localization_weight: 1.0 } normalize_loss_by_num_matches: true post_processing { batch_non_max_suppression { score_threshold: 1e-8 iou_threshold: 0.6 max_detections_per_class: 100 max_total_detections: 100 } score_converter: SIGMOID } } }
train_config: { batch_size: 1 optimizer { rms_prop_optimizer: { learning_rate: { exponential_decay_learning_rate { initial_learning_rate: 0.004 decay_steps: 800720 decay_factor: 0.95 } } momentum_optimizer_value: 0.9 decay: 0.9 epsilon: 1.0 } } fine_tune_checkpoint: "" from_detection_checkpoint: true
Note: The below line limits the training process to 200K steps, which we
empirically found to be sufficient enough to train the pets dataset. This
effectively bypasses the learning rate schedule (the learning rate will
never decay). Remove the below line to train indefinitely.
num_steps: 20000 data_augmentation_options { random_horizontal_flip { } } data_augmentation_options { ssd_random_crop { } } }
train_input_reader: { tf_record_input_reader { input_path: "I:/work/Other/L3C_Glass_skew/Model_256_256_DM_P125/data/train.record" } label_map_path: "I:/work/Other/L3C_Glass_skew/Label.pbtxt" }
eval_config: { num_examples: 2000
Note: The below line limits the evaluation process to 10 evaluations.
Remove the below line to evaluate indefinitely.
max_evals: 10 }
eval_input_reader: { tf_record_input_reader { input_path: "I:/work/Other/skew/Model_256_256_DM_P125/data/train.record" } label_map_path: "I:/work/Other/skew/Label.pbtxt" shuffle: false num_readers: 1 }
kissste
weiran-work
manoj7410
abhinavrawat27
Hi
I retrain with MobileNet SSD V1 with 256x256 DM=0.125，but I got an issue as follw Could anybody solve the issue ? pi@raspberrypi:~/AIY-voice-kit-python/src/examples/vision $ ./object_detection.py --input glassskew_Resized.png --output glassskew_detected.png Traceback (most recent call last): File "/opt/aiy/projects-python/src/aiy/_drivers/_spicomm.py", line 128, in transact fcntl.ioctl(self._dev, SPICOMM_IOCTL_TRANSACT, self._tbuf) OSError: [Errno 14] Bad address
During handling of the above exception, another exception occurred:
Traceback (most recent call last): File "./object_detection.py", line 39, in main result = inference.run(image_center) File "/opt/aiy/projects-python/src/aiy/vision/inference.py", line 100, in run return self._engine.image_inference(self._key, image, params) File "/opt/aiy/projects-python/src/aiy/vision/inference.py", line 327, in image_inference return self._communicate(request).inference_result File "/opt/aiy/projects-python/src/aiy/vision/inference.py", line 191, in _communicate response.ParseFromString(self._transport.send(request.SerializeToString())) File "/opt/aiy/projects-python/src/aiy/_drivers/_transport.py", line 33, in send return self._spicomm.transact(request) File "/opt/aiy/projects-python/src/aiy/_drivers/_spicomm.py", line 143, in transact raise SpicommInternalError aiy._drivers._spicomm.SpicommInternalError
During handling of the above exception, another exception occurred:
Traceback (most recent call last): File "./object_detection.py", line 50, in
main()
File "./object_detection.py", line 46, in main
image.save(args.output)
File "/opt/aiy/projects-python/src/aiy/vision/inference.py", line 110, in exit
self.close()
File "/opt/aiy/projects-python/src/aiy/vision/inference.py", line 103, in close
self._engine.unload_model(self._key)
File "/opt/aiy/projects-python/src/aiy/vision/inference.py", line 251, in unload_model
self._communicate(request)
File "/opt/aiy/projects-python/src/aiy/vision/inference.py", line 194, in _communicate
raise InferenceException(response.status.message)
aiy.vision.inference.InferenceException: UnloadModel: Model 'object_detection' is not loaded.