So I'm trying to retrain a fast_rcnn object detection model, with just one class, which I've attempted to run both locally (on a VM) and through ML engine. I keep running into the same error in regards to the train_config file however, which is an adaptation of the faster_rcnn_resnet50_coco.config configuration:
Traceback (most recent call last): File "/usr/lib/python2.7/runpy.py", line 174, in _run_module_as_main "main", fname, loader, pkg_name) File "/usr/lib/python2.7/runpy.py", line 72, in _run_code exec code in run_globals File "/root/.local/lib/python2.7/site-packages/trainer/task.py", line 171, in tf.app.run(main=main, argv=[sys.argv[0]] + unparsed) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/platform/app.py", line 125, in run _sys.exit(main(argv)) File "/root/.local/lib/python2.7/site-packages/trainer/task.py", line 142, in main tf.estimator.train_and_evaluate(estimator, train_spec, eval_specs[0]) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/estimator/training.py", line 471, in train_and_evaluate return executor.run() File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/estimator/training.py", line 637, in run getattr(self, task_to_run)() File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/estimator/training.py", line 674, in run_master self._start_distributed_training(saving_listeners=saving_listeners) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/estimator/training.py", line 788, in _start_distributed_training saving_listeners=saving_listeners) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/estimator/estimator.py", line 354, in train loss = self._train_model(input_fn, hooks, saving_listeners) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/estimator/estimator.py", line 1207, in _train_model return self._train_model_default(input_fn, hooks, saving_listeners) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/estimator/estimator.py", line 1234, in _train_model_default input_fn, model_fn_lib.ModeKeys.TRAIN)) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/estimator/estimator.py", line 1075, in _get_features_and_labels_from_input_fn self._call_input_fn(input_fn, mode)) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/estimator/estimator.py", line 1162, in _call_input_fn return input_fn(**kwargs) File "/root/.local/lib/python2.7/site-packages/trainer/object_detection/inputs.py", line 375, in _train_input_fn raise TypeError('For training mode, the
train_configmust be a ' TypeError: For training mode, thetrain_configmust be a train_pb2.TrainConfig.
I've spent a long time looking for the potential cause of this issue in my config file but I can't see what the problem is. There doesn't seem to be any documentation mentioning this apart from the TF source code itself. Any insight would be greatly appreciated!
model {
faster_rcnn {
num_classes: 1
image_resizer {
fixed_shape_resizer {
height: 600
width: 205
}
}
feature_extractor {
type: 'faster_rcnn_resnet50'
first_stage_features_stride: 16
}
first_stage_anchor_generator {
grid_anchor_generator {
scales: [0.25, 0.5, 1.0, 2.0]
aspect_ratios: [0.5, 1.0, 2.0]
height_stride: 16
width_stride: 16
}
}
first_stage_box_predictor_conv_hyperparams {
op: CONV
regularizer {
l2_regularizer {
weight: 0.0
}
}
initializer {
truncated_normal_initializer {
stddev: 0.01
}
}
}
first_stage_nms_score_threshold: 0.0
first_stage_nms_iou_threshold: 0.7
first_stage_max_proposals: 300
first_stage_localization_loss_weight: 2.0
first_stage_objectness_loss_weight: 1.0
initial_crop_size: 14
maxpool_kernel_size: 2
maxpool_stride: 2
second_stage_box_predictor {
mask_rcnn_box_predictor {
use_dropout: false
dropout_keep_probability: 1.0
fc_hyperparams {
op: FC
regularizer {
l2_regularizer {
weight: 0.0
}
}
initializer {
variance_scaling_initializer {
factor: 1.0
uniform: true
mode: FAN_AVG
}
}
}
}
}
second_stage_post_processing {
batch_non_max_suppression {
score_threshold: 0.0
iou_threshold: 0.6
max_detections_per_class: 100
max_total_detections: 300
}
score_converter: SOFTMAX
}
second_stage_localization_loss_weight: 2.0
second_stage_classification_loss_weight: 1.0
}
}
train_config: {
batch_size: 5
optimizer {
momentum_optimizer: {
learning_rate: {
exponential_decay_learning_rate {
initial_learning_rate: 0.0003
decay_steps: 500
decay_factor: 0.9
}
}
momentum_optimizer_value: 0.9
}
use_moving_average: false
}
gradient_clipping_by_norm: 10.0
fine_tune_checkpoint: "gs://ml-pipeline/checkpoints/fast_rcnn_resnet50/model.ckpt-5500"
from_detection_checkpoint: true
load_all_detection_checkpoint_vars: true
num_steps: 2000
data_augmentation_options {
normalize_image {
}
random_pixel_value_scale {
}
random_adjust_brightness {
}
random_jitter_boxes {
}
random_pad_image {
}
}
max_number_of_boxes: 35
}
train_input_reader: {
tf_record_input_reader {
input_path: "gs://ml-pipeline/data/tf-records/train.record"
}
label_map_path: "gs://ml-pipeline/story_label_map.pbtxt"
}
eval_config {
num_examples: 54
num_visualizations: 54
eval_interval_secs: 10
max_evals: 1
#use_moving_averages: false
}
eval_input_reader: {
tf_record_input_reader {
input_path: "gs://ml-pipeline/data/tf-records/test.record"
}
label_map_path: "gs://ml-pipeline/story_label_map.pbtxt"
shuffle: false
num_readers: 1
}
