Load Trained Model From Checkpoint - NotFoundError

Please make sure that this is a build/installation issue. As per our GitHub Policy, we only address code/doc bugs, performance issues, feature requests and build/installation issues on GitHub. tag:build_template

System information

OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Windows 10 64bit
TensorFlow installed from (source or binary):
https://github.com/tensorflow/models
TensorFlow version: 2
Python version: 3.7.3
Installed using virtualenv? pip? conda?: conda and pip
Describe the problem
I have downloaded and installed tensorflow, and I'm attempting to train a custom model, but keep getting runtime errors or notfounderrors to do with tenorflow lib files.
Provide the exact sequence of commands / steps that you executed before running into the problem
`WORKSPACE_PATH = 'Tensorflow/workspace'
SCRIPTS_PATH = 'Tensorflow/scripts'
APIMODEL_PATH = 'Tensorflow/models'
ANNOTATION_PATH = WORKSPACE_PATH+'/annotations'
IMAGE_PATH = WORKSPACE_PATH+'/images'
MODEL_PATH = WORKSPACE_PATH+'/models'
PRETRAINED_MODEL_PATH = WORKSPACE_PATH+'/pre-trained-models'
CONFIG_PATH = MODEL_PATH+'/my_ssd_mobnet/pipeline.config'
CHECKPOINT_PATH = MODEL_PATH+'/my_ssd_mobnet/'

labels = [{'name':'title', 'id':1}, {'name':'xaxis', 'id':2}, {'name':'yaxis', 'id':3}, {'name':'bar', 'id':4}, {'name':'key', 'id':5}]

with open(ANNOTATION_PATH + '\label_map.pbtxt', 'w') as f:
for label in labels:
f.write('item { \n')
f.write('\tname:'{}'\n'.format(label['name']))
f.write('\tid:{}\n'.format(label['id']))
f.write('}\n')

!python {SCRIPTS_PATH + '/generate_tfrecord.py'} -x {IMAGE_PATH + '/train'} -l {ANNOTATION_PATH + '/label_map.pbtxt'} -o {ANNOTATION_PATH + '/train.record'}
!python {SCRIPTS_PATH + '/generate_tfrecord.py'} -x{IMAGE_PATH + '/test'} -l {ANNOTATION_PATH + '/label_map.pbtxt'} -o {ANNOTATION_PATH + '/test.record'}

!cd Tensorflow && git clone https://github.com/tensorflow/models

CUSTOM_MODEL_NAME = 'my_ssd_mobnet'
!mkdir {'Tensorflow\workspace\models'+CUSTOM_MODEL_NAME}
!cp {PRETRAINED_MODEL_PATH+'/ssd_mobilenet_v2_fpnlite_320x320_coco17_tpu-8/pipeline.config'} {MODEL_PATH+'/'+CUSTOM_MODEL_NAME}

import tensorflow as tf
from object_detection.utils import config_util
from object_detection.protos import pipeline_pb2
from google.protobuf import text_format

CONFIG_PATH = MODEL_PATH+'/'+CUSTOM_MODEL_NAME+'/pipeline.config'

config = config_util.get_configs_from_pipeline_file(CONFIG_PATH)
config
{'model': ssd {
num_classes: 90
image_resizer {
fixed_shape_resizer {
height: 320
width: 320
}
}
feature_extractor {
type: "ssd_mobilenet_v2_fpn_keras"
depth_multiplier: 1.0
min_depth: 16
conv_hyperparams {
regularizer {
l2_regularizer {
weight: 3.9999998989515007e-05
}
}
initializer {
random_normal_initializer {
mean: 0.0
stddev: 0.009999999776482582
}
}
activation: RELU_6
batch_norm {
decay: 0.996999979019165
scale: true
epsilon: 0.0010000000474974513
}
}
use_depthwise: true
override_base_feature_extractor_hyperparams: true
fpn {
min_level: 3
max_level: 7
additional_layer_depth: 128
}
}
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
use_matmul_gather: true
}
}
similarity_calculator {
iou_similarity {
}
}
box_predictor {
weight_shared_convolutional_box_predictor {
conv_hyperparams {
regularizer {
l2_regularizer {
weight: 3.9999998989515007e-05
}
}
initializer {
random_normal_initializer {
mean: 0.0
stddev: 0.009999999776482582
}
}
activation: RELU_6
batch_norm {
decay: 0.996999979019165
scale: true
epsilon: 0.0010000000474974513
}
}
depth: 128
num_layers_before_predictor: 4
kernel_size: 3
class_prediction_bias_init: -4.599999904632568
share_prediction_tower: true
use_depthwise: true
}
}
anchor_generator {
multiscale_anchor_generator {
min_level: 3
max_level: 7
anchor_scale: 4.0
aspect_ratios: 1.0
aspect_ratios: 2.0
aspect_ratios: 0.5
scales_per_octave: 2
}
}
post_processing {
batch_non_max_suppression {
score_threshold: 9.99999993922529e-09
iou_threshold: 0.6000000238418579
max_detections_per_class: 100
max_total_detections: 100
use_static_shapes: false
}
score_converter: SIGMOID
}
normalize_loss_by_num_matches: true
loss {
localization_loss {
weighted_smooth_l1 {
}
}
classification_loss {
weighted_sigmoid_focal {
gamma: 2.0
alpha: 0.25
}
}
classification_weight: 1.0
localization_weight: 1.0
}
encode_background_as_zeros: true
normalize_loc_loss_by_codesize: true
inplace_batchnorm_update: true
freeze_batchnorm: false
}, 'train_config': batch_size: 128
data_augmentation_options {
random_horizontal_flip {
}
}
data_augmentation_options {
random_crop_image {
min_object_covered: 0.0
min_aspect_ratio: 0.75
max_aspect_ratio: 3.0
min_area: 0.75
max_area: 1.0
overlap_thresh: 0.0
}
}
sync_replicas: true
optimizer {
momentum_optimizer {
learning_rate {
cosine_decay_learning_rate {
learning_rate_base: 0.07999999821186066
total_steps: 50000
warmup_learning_rate: 0.026666000485420227
warmup_steps: 1000
}
}
momentum_optimizer_value: 0.8999999761581421
}
use_moving_average: false
}
fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED"
num_steps: 50000
startup_delay_steps: 0.0
replicas_to_aggregate: 8
max_number_of_boxes: 100
unpad_groundtruth_tensors: false
fine_tune_checkpoint_type: "classification"
fine_tune_checkpoint_version: V2, 'train_input_config': label_map_path: "PATH_TO_BE_CONFIGURED"
tf_record_input_reader {
input_path: "PATH_TO_BE_CONFIGURED"
}, 'eval_config': metrics_set: "coco_detection_metrics"
use_moving_averages: false, 'eval_input_configs': [label_map_path: "PATH_TO_BE_CONFIGURED"
shuffle: false
num_epochs: 1
tf_record_input_reader {
input_path: "PATH_TO_BE_CONFIGURED"
}
], 'eval_input_config': label_map_path: "PATH_TO_BE_CONFIGURED"
shuffle: false
num_epochs: 1
tf_record_input_reader {
input_path: "PATH_TO_BE_CONFIGURED"
}}
pipeline_config = pipeline_p

pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
with tf.io.gfile.GFile(CONFIG_PATH, "r") as f:
proto_str = f.read()
text_format.Merge(proto_str, pipeline_config)
pipeline_config.model.ssd.num_classes = 2
pipeline_config.train_config.batch_size = 4
pipeline_config.train_config.fine_tune_checkpoint = PRETRAINED_MODEL_PATH+'/ssd_mobilenet_v2_fpnlite_320x320_coco17_tpu-8/checkpoint/ckpt-0'
pipeline_config.train_config.fine_tune_checkpoint_type = "detection"
pipeline_config.train_input_reader.label_map_path= ANNOTATION_PATH + '/label_map.pbtxt'
pipeline_config.train_input_reader.tf_record_input_reader.input_path[:] = [ANNOTATION_PATH + '/train.record']
pipeline_config.eval_input_reader[0].label_map_path = ANNOTATION_PATH + '/label_map.pbtxt'
pipeline_config.eval_input_reader[0].tf_record_input_reader.input_path[:] = [ANNOTATION_PATH + '/test.record']

config_text = text_format.MessageToString(pipeline_config)
with tf.io.gfile.GFile(CONFIG_PATH, "wb") as f:
f.write(config_text)

print("""python {}/research/object_detection/model_main_tf2.py --model_dir={}/{} --pipeline_config_path={}/{}/pipeline.config --num_train_steps=5000""".format(APIMODEL_PATH, MODEL_PATH,CUSTOM_MODEL_NAME,MODEL_PATH,CUSTOM_MODEL_NAME))

import os
from object_detection.utils import label_map_util
from object_detection.utils import visualization_utils as viz_utils
from object_detection.builders import model_builder

Load pipeline config and build a detection model
configs = config_util.get_configs_from_pipeline_file(CONFIG_PATH)
detection_model = model_builder.build(model_config=configs['model'], is_training=False)

Restore checkpoint
ckpt = tf.compat.v2.train.Checkpoint(model=detection_model)
ckpt.restore(os.path.join(CHECKPOINT_PATH, 'ckpt-6')).expect_partial()

@tf.function
def detect_fn(image):
image, shapes = detection_model.preprocess(image)
prediction_dict = detection_model.predict(image, shapes)
detections = detection_model.postprocess(prediction_dict, shapes)
return detections
#---------------------This Is Where The error Happens ----------------------------------------`

Error Message
`---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\training\py_checkpoint_reader.py in NewCheckpointReader(filepattern)
94 try:
---> 95 return CheckpointReader(compat.as_bytes(filepattern))
96 # TODO(b/143319754): Remove the RuntimeError casting logic once we resolve the

RuntimeError: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for Tensorflow/workspace/models/my_ssd_mobnet/ckpt-6

During handling of the above exception, another exception occurred:

NotFoundError Traceback (most recent call last)
C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\training\tracking\util.py in restore(self, save_path, options)
2259 try:
-> 2260 status = self.read(save_path, options=options)
2261 except errors_impl.NotFoundError:

C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\training\tracking\util.py in read(self, save_path, options)
2147 options = options or checkpoint_options.CheckpointOptions()
-> 2148 return self._saver.restore(save_path=save_path, options=options)
2149

C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\training\tracking\util.py in restore(self, save_path, options)
1291 return InitializationOnlyStatus(self._graph_view, ops.uid())
-> 1292 reader = py_checkpoint_reader.NewCheckpointReader(save_path)
1293 graph_building = not context.executing_eagerly()

C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\training\py_checkpoint_reader.py in NewCheckpointReader(filepattern)
98 except RuntimeError as e:
---> 99 error_translator(e)

C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\training\py_checkpoint_reader.py in error_translator(e)
34 'matching files for') in error_message:
---> 35 raise errors_impl.NotFoundError(None, None, error_message)
36 elif 'Sliced checkpoints are not supported' in error_message or (

NotFoundError: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for Tensorflow/workspace/models/my_ssd_mobnet/ckpt-6

During handling of the above exception, another exception occurred:

NotFoundError Traceback (most recent call last)
in
5 # Restore checkpoint
6 ckpt = tf.compat.v2.train.Checkpoint(model=detection_model)
----> 7 ckpt.restore(os.path.join(CHECKPOINT_PATH, 'ckpt-6')).expect_partial()
8
9 @tf.function

C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\training\tracking\util.py in restore(self, save_path, options)
2263 None, None,
2264 "Could not find checkpoint or SavedModel at {}."
-> 2265 .format(orig_save_path))
2266 # Create the save counter now so it gets initialized with other variables
2267 # when graph building. Creating it earlier would lead to errors when using,

NotFoundError: Could not find checkpoint or SavedModel at Tensorflow/workspace/models/my_ssd_mobnet/ckpt-6.`