Permalink
* Merged commit includes the following changes: 204316992 by Zhichao Lu: Update docs to prepare inputs -- 204309254 by Zhichao Lu: Update running_pets.md to use new binaries and correct a few things in running_on_cloud.md -- 204306734 by Zhichao Lu: Move old binaries into legacy folder and add deprecation notice. -- 204267757 by Zhichao Lu: Fixing a problem in VRD evaluation with missing ground truth annotations for images that do not contain objects from 62 groundtruth classes. -- 204167430 by Zhichao Lu: This fixes a flaky losses test failure. -- 203670721 by Zhichao Lu: Internal change. -- 203569388 by Zhichao Lu: Internal change 203546580 by Zhichao Lu: * Expand TPU compatibility g3doc with config snippets * Change mscoco dataset path in sample configs to the sharded versions -- 203325694 by Zhichao Lu: Make merge_multiple_label_boxes work for model_main code path. -- 203305655 by Zhichao Lu: Remove the 1x1 conv layer before pooling in MobileNet-v1-PPN feature extractor. -- 203139608 by Zhichao Lu: - Support exponential_decay with burnin learning rate schedule. - Add the minimum learning rate option. - Make the exponential decay start only after the burnin steps. -- 203068703 by Zhichao Lu: Modify create_coco_tf_record.py to output sharded files. -- 203025308 by Zhichao Lu: Add an option to share the prediction tower in WeightSharedBoxPredictor. -- 203024942 by Zhichao Lu: Move ssd mobilenet v1 ppn configs to third party. -- 202901259 by Zhichao Lu: Delete obsolete ssd mobilenet v1 focal loss configs and update pets dataset path -- 202894154 by Zhichao Lu: Move all TPU compatible ssd mobilenet v1 coco14/pet configs to third party. -- 202861774 by Zhichao Lu: Move Retinanet (SSD + FPN + Shared box predictor) configs to third_party. -- PiperOrigin-RevId: 204316992 * Add original files back.
# Embedded SSD with Mobilenet v1 configuration for MSCOCO 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: 90 | |
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: 5 | |
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: 'embedded_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: 32 | |
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: "/PATH_TO_BE_CONFIGURED/model.ckpt" | |
data_augmentation_options { | |
random_horizontal_flip { | |
} | |
} | |
data_augmentation_options { | |
ssd_random_crop { | |
} | |
} | |
} | |
train_input_reader: { | |
tf_record_input_reader { | |
input_path: "PATH_TO_BE_CONFIGURED/mscoco_train.record-?????-of-00100" | |
} | |
label_map_path: "PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt" | |
} | |
eval_config: { | |
num_examples: 8000 | |
use_moving_averages: true | |
} | |
eval_input_reader: { | |
tf_record_input_reader { | |
input_path: "PATH_TO_BE_CONFIGURED/mscoco_val.record-?????-of-00010" | |
} | |
label_map_path: "PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt" | |
shuffle: false | |
num_readers: 1 | |
} |