Hi! Thanks for your job in the repo!

Can you provide information on how you got the SSD-models:

• SSD-MobileNet v1 and
• SSDLite-MobileNet v2?

I see that the models are trained on COCO with 91-labels.
Are they just a copy from tensorflow detection_model_zoo or there was an additional training?

\tensorflow\core\framework\op_kernel.cc:943] OpKernel ('op: "BestSplits" device_type: "CPU"') for unknown op: BestSplits
\tensorflow\core\framework\op_kernel.cc:943] OpKernel ('op: "CountExtremelyRandomStats" device_type: "CPU"') for unknown op: CountExtremelyRandomStats
\tensorflow\core\framework\op_kernel.cc:943] OpKernel ('op: "FinishedNodes" device_type: "CPU"') for unknown op: FinishedNodes
\tensorflow\core\framework\op_kernel.cc:943] OpKernel ('op: "GrowTree" device_type: "CPU"') for unknown op: GrowTree
\tensorflow\core\framework\op_kernel.cc:943] OpKernel ('op: "ReinterpretStringToFloat" device_type: "CPU"') for unknown op: ReinterpretStringToFloat
\tensorflow\core\framework\op_kernel.cc:943] OpKernel ('op: "SampleInputs" device_type: "CPU"') for unknown op: SampleInputs
\tensorflow\core\framework\op_kernel.cc:943] OpKernel ('op: "ScatterAddNdim" device_type: "CPU"') for unknown op: ScatterAddNdim
\tensorflow\core\framework\op_kernel.cc:943] OpKernel ('op: "TopNInsert" device_type: "CPU"') for unknown op: TopNInsert
\tensorflow\core\framework\op_kernel.cc:943] OpKernel ('op: "TopNRemove" device_type: "CPU"') for unknown op: TopNRemove
\tensorflow\core\framework\op_kernel.cc:943] OpKernel ('op: "TreePredictions" device_type: "CPU"') for unknown op: TreePredictions
\tensorflow\core\framework\op_kernel.cc:943] OpKernel ('op: "UpdateFertileSlots" device_type: "CPU"') for unknown op: UpdateFertileSlots

Hello!

I am developing a mobile application for grocery detection. Currently I have stuck on custom object detection training at mobilenet convertion to tflite format.

I have raised an issue at offical TensorFlow repo, but unfortunately there is no answer. Thread: tensorflow/models#8786.

All results I got were raising exepction on load by Flutters tflite module.

Suprisingly mobilenet mentioned in Yours repos README (https://drive.google.com/file/d/1Ha9yfjkweCatEo6UoZgZyHMeyIBGe5FO/view) is loaded properly and correctly detects objects on recordings.

This feature is crucial for application, to be useful.

I would be grateful if You could share some knowledge about:

• how to convert .pd SSD MobileNet to THIS (https://drive.google.com/file/d/1Ha9yfjkweCatEo6UoZgZyHMeyIBGe5FO/view) format (scripts and details like Python and TensorFlow version)

Example scenario:

1. Download SSD MobileNet from tfs' offical repo (https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/tf1_detection_zoo.md) for example: ssd_mobilenet_v2_quantized_coco
2. Convert it to .tflite format
3. SSD MobileNet is loaded with success by flutter and correctly detects objects

I have followed several tutorials, but it seems like they are not a solution.

I would be pleased for an answer

No module named 'utils.ssd_mobilenet_utils'

it does not work，

thanks

Hello,after following your readme file,I cannot get any result but some warnings after running your code.

`E:\conda\envs\mobilenet-ssd-tensorflow\lib\site-packages\tensorflow\python\framework\ops.py:923: DeprecationWarning: builtin type EagerTensor has no module attribute
EagerTensor = c_api.TFE_Py_InitEagerTensor(_EagerTensorBase)

E:\conda\envs\mobilenet-ssd-tensorflow\lib\site-packages\tensorflow\python\util\tf_inspect.py:75: DeprecationWarning: inspect.getargspec() is deprecated, use inspect.signature() instead
return _inspect.getargspec(target)`

Traceback (most recent call last):
File "test_tiny_yolo.py", line 104, in
yolo_model = load_model("model_data/tiny-yolo.h5")
File "C:\Users\Admin\Anaconda3\envs\tfdeeplearning\lib\site-packages\keras\models.py", line 243, in load_model
model = model_from_config(model_config, custom_objects=custom_objects)
File "C:\Users\Admin\Anaconda3\envs\tfdeeplearning\lib\site-packages\keras\models.py", line 317, in model_from_config
return layer_module.deserialize(config, custom_objects=custom_objects)
File "C:\Users\Admin\Anaconda3\envs\tfdeeplearning\lib\site-packages\keras\layers_init_.py", line 55, in deserialize
printable_module_name='layer')
File "C:\Users\Admin\Anaconda3\envs\tfdeeplearning\lib\site-packages\keras\utils\generic_utils.py", line 144, in deserialize_keras_object
list(custom_objects.items())))
File "C:\Users\Admin\Anaconda3\envs\tfdeeplearning\lib\site-packages\keras\engine\topology.py", line 2524, in from_config
process_node(layer, node_data)
File "C:\Users\Admin\Anaconda3\envs\tfdeeplearning\lib\site-packages\keras\engine\topology.py", line 2481, in process_node
layer(input_tensors[0], **kwargs)
File "C:\Users\Admin\Anaconda3\envs\tfdeeplearning\lib\site-packages\keras\engine\topology.py", line 619, in call
output = self.call(inputs, **kwargs)
File "C:\Users\Admin\Anaconda3\envs\tfdeeplearning\lib\site-packages\keras\layers\advanced_activations.py", line 46, in call
return K.relu(inputs, alpha=self.alpha)
File "C:\Users\Admin\Anaconda3\envs\tfdeeplearning\lib\site-packages\keras\backend\tensorflow_backend.py", line 2921, in relu
x = tf.nn.leaky_relu(x, alpha)
AttributeError: module 'tensorflow.python.ops.nn' has no attribute 'leaky_relu'
swig/python detected a memory leak of type 'int64_t *', no destructor found.