How can I run mobiledet model successfully with the pretrained model in TF1 model zoo from TensorFlow object detection api？ - tensorflow

Question

I want to test the mobiledet model provided in the TF1 model zoo from TensorFlow object detection api. tf1 object detection model zoo
since the pretrained files contain both the pb file and the ckpt files the Screenshot of ckpt files.
So, I have tried two methods to load the pretrained model to do inference.
Firstly, I tried to load the tflite_graph.pb directly.I encountered the following problem, I tried to change the tf version, but it still did not solve.
The code is like this:
MODEL_DIR = '/tf_ckpts/ssdlite_mobiledet_cpu_320x320_coco_2020_05_19/'
MODEL_CHECK_FILE = os.path.join(MODEL_DIR, 'tflite_graph.pb')
graph = tf.Graph()
with graph.as_default():
graph_def = tf.GraphDef()
with tf.gfile.Open(MODEL_CHECK_FILE,'rb') as f:
graph_def.ParseFromString(f.read())
tf.import_graph_def(graph_def, name='')
Traceback (most recent call last):
File "/home/zhaoxin/workspace/models-1.12.0/research/inference_demo.py", line 41, in <module>
tf.import_graph_def(graph_def, name='')
File "/home/zhaoxin/tools/miniconda3/envs/tf115/lib/python3.6/site-packages/tensorflow_core/python/util/deprecation.py", line 507, in new_func
return func(*args, **kwargs)
File "/home/zhaoxin/tools/miniconda3/envs/tf115/lib/python3.6/site-packages/tensorflow_core/python/framework/importer.py", line 405, in import_graph_def
producer_op_list=producer_op_list)
File "/home/zhaoxin/tools/miniconda3/envs/tf115/lib/python3.6/site-packages/tensorflow_core/python/framework/importer.py", line 505, in _import_graph_def_internal
raise ValueError(str(e))
ValueError: NodeDef mentions attr 'exponential_avg_factor' not in Op<name=FusedBatchNormV3; signature=x:T, scale:U, offset:U, mean:U, variance:U -> y:T, batch_mean:U, batch_variance:U, reserve_space_1:U, reserve_space_2:U, reserve_space_3:U; attr=T:type,allowed=[DT_HALF, DT_BFLOAT16, DT_FLOAT]; attr=U:type,allowed=[DT_FLOAT]; attr=epsilon:float,default=0.0001; attr=data_format:string,default="NHWC",allowed=["NHWC", "NCHW"]; attr=is_training:bool,default=true>; NodeDef: {{node FeatureExtractor/MobileDetCPU/Conv/BatchNorm/FusedBatchNormV3}}. (Check whether your GraphDef-interpreting binary is up to date with your GraphDef-generating binary.).
Then, I tried to load the ckpt files to run the model.
mobiledet = 'tf_ckpts/ssdlite_mobiledet_cpu_320x320_coco_2020_05_19/'
meta_path = mobiledet+'model.ckpt-400000.meta'
ckpt_path = mobiledet+'model.ckpt-400000'
with tf.Session() as sess:
saver=tf.train.import_meta_graph(meta_path)
saver.restore(sess, ckpt_path)
graph = tf.get_default_graph()
The error like this:
Traceback (most recent call last):
File "/home/zhaoxin/workspace/models-1.12.0/research/tf_load.py", line 15, in <module>
saver=tf.train.import_meta_graph(meta_path)
File "/home/zhaoxin/tools/miniconda3/envs/tf115/lib/python3.6/site-packages/tensorflow_core/python/training/saver.py", line 1453, in import_meta_graph
**kwargs)[0]
File "/home/zhaoxin/tools/miniconda3/envs/tf115/lib/python3.6/site-packages/tensorflow_core/python/training/saver.py", line 1477, in _import_meta_graph_with_return_elements
**kwargs))
File "/home/zhaoxin/tools/miniconda3/envs/tf115/lib/python3.6/site-packages/tensorflow_core/python/framework/meta_graph.py", line 809, in import_scoped_meta_graph_with_return_elements
return_elements=return_elements)
File "/home/zhaoxin/tools/miniconda3/envs/tf115/lib/python3.6/site-packages/tensorflow_core/python/util/deprecation.py", line 507, in new_func
return func(*args, **kwargs)
File "/home/zhaoxin/tools/miniconda3/envs/tf115/lib/python3.6/site-packages/tensorflow_core/python/framework/importer.py", line 405, in import_graph_def
producer_op_list=producer_op_list)
File "/home/zhaoxin/tools/miniconda3/envs/tf115/lib/python3.6/site-packages/tensorflow_core/python/framework/importer.py", line 501, in _import_graph_def_internal
graph._c_graph, serialized, options) # pylint: disable=protected-access
tensorflow.python.framework.errors_impl.NotFoundError: Op type not registered 'LegacyParallelInterleaveDatasetV2' in binary running on localhost.localdomain. Make sure the Op and Kernel are registered in the binary running in this process. Note that if you are loading a saved graph which used ops from tf.contrib, accessing (e.g.) `tf.contrib.resampler` should be done before importing the graph, as contrib ops are lazily registered when the module is first accessed.
It seems that the loading errors of the above two methds are caused by the inconsistency of the tf version, but I have tried many tf versions and failed to solve it. Has anyone successfully run the mobiledet model in TF1 object detection model zoo?
OS: linux
TF version: tf 1.15

Answer 1

#Shane Zhao - are you planning on training with custom dataset or are you using the pretrained graph as is? The version of Tensorflow should only matter during training to the best of my knowledge. Anyways please refer this demo from Google in Colab - https://colab.research.google.com/github/luxonis/depthai-ml-training/blob/master/colab-notebooks/Easy_Object_Detection_Demo_Training.ipynb#scrollTo=JDddx2rPfex9