Tensor control point missing input tensor node

Question

Tensor control point missing input tensor node

(please forgive my long post, I really appreciate your help)

I am training squeezeDet model for pascal style VOC style custom data according to training code from repository HERE

the model's saved control point works well, as I see acceptable performance.

Now I'm trying to freeze the model for deployment using coreML to find out how performance is on the mobile platform. The authors of the script publish only the results of the report in the GPU environment in their research work.

I follow the recommended steps according to the tensor flow, my commands below

Firstly,

I am writing a graph from a milestone metafile

path_to_ckpt_meta = rootdir + "model.ckpt-355000.meta"
path_to_ckpt_data = rootdir + "model.ckpt-355000"

sess = tf.Session(config=tf.ConfigProto(allow_soft_placement=True))

saver = tf.train.import_meta_graph(path_to_ckpt_meta)
saver.restore(sess, path_to_ckpt_data)

tf.train.write_graph(tf.get_default_graph().as_graph_def(), rootdir, "model_ckpt_355000_graph_V2.pb", False)

Now

, . .

, inspect_checkpoint.py , image_input. .

, tenszeflow freeze_graph.py

python ./tensorflow/python/tools/freeze_graph.py  \
--input_graph=path-to-dir/train/model_ckpt_355000_graph.pb \
--input_checkpoint=path-to-dir/train/model.ckpt-355000 \
--output_graph=path-to-dir/train/frozen_sqdt_ckpt_355000.pb \
--output_node_names=bbox/trimming/bbox,probability/score,probability/class_idx

freeze_graph .

, sumize_graph

bazel-bin/tensorflow/tools/graph_transforms/summarize_graph --in_graph=/tmp/logs/squeezeDet_NewDataset_test01_March02/train/frozen_sqdt_ckpt_355000.pb

No inputs spotted.
No variables spotted.
Found 3 possible outputs: (name=bbox/trimming/bbox, op=Transpose) (name=probability/score, op=Max) (name=probability/class_idx, op=ArgMax) 
Found 2703452 (2.70M) const parameters, 0 (0) variable parameters, and 0 control_edges
Op types used: 130 Const, 68 Identity, 32 BiasAdd, 32 Conv2D, 31 Relu, 15 Mul, 14 Add, 10 ConcatV2, 9 Sub, 5 RealDiv, 5 Reshape, 4 Maximum, 4 Minimum, 3 StridedSlice, 3 MaxPool, 2 Exp, 2 Greater, 2 Cast, 2 Select, 1 Transpose, 1 Softmax, 1 Sigmoid, 1 Unpack, 1 RandomUniform, 1 QueueDequeueManyV2, 1 Pack, 1 Max, 1 Floor, 1 FIFOQueueV2, 1 ArgMax
To use with tensorflow/tools/benchmark:benchmark_model try these arguments:
bazel run tensorflow/tools/benchmark:benchmark_model -- --graph=/tmp/logs/squeezeDet_NewDataset_test01_March02/train/frozen_sqdt_ckpt_355000.pb --show_flops --input_layer= --input_layer_type= --input_layer_shape= --output_layer=bbox/trimming/bbox,probability/score,probability/class_idx