search

nwesem / mtcnn_facenet_cpp_tensorRT

Face Recognition on NVIDIA Jetson (Nano) using TensorRT
GNU General Public License v3.0
203 stars 72 forks source link

Error with facenet.pb to facenet.uff #10

Closed nagorntow closed 4 years ago

nagorntow commented 4 years ago

Using output node dimension/LeakyRelu Using output node orientation/l2_normalize Using output node confidence/Softmax Converting to UFF graph Traceback (most recent call last): File "./step01_pb_to_uff.py", line 32, in output_filename=uff_file, text=False) File "/usr/lib/python3.6/dist-packages/uff/converters/tensorflow/conversion_helpers.py", line 178, in from_tensorflow debug_mode=debug_mode) File "/usr/lib/python3.6/dist-packages/uff/converters/tensorflow/converter.py", line 94, in convert_tf2uff_graph uff_graph, input_replacements, debug_mode=debug_mode) File "/usr/lib/python3.6/dist-packages/uff/converters/tensorflow/converter.py", line 62, in convert_tf2uff_node raise UffException(str(name) + " was not found in the graph. Please use the -l option to list nodes in the graph.") uff.model.exceptions.UffException: confidence/Softmax was not found in the graph. Please use the -l option to list nodes in the graph.

nwesem commented 4 years ago

@nagorntow can you give more info what you are using as your input file?

nagorntow commented 4 years ago

I using file download from github.com/apollo-time/facenet/raw/master/model/resnet/facenet.pb and change name file to sample.pb

run file commend "python3 step01_pb_to_uff.py"

nwesem commented 4 years ago

did you change the input path (variable is called pb_file) to path/to/your/sample.pb in this line?

nwesem commented 4 years ago

I tested this with Jetpack 4.4 and it is properly working with tensorflow 1.15 and python 3.6