-
Notifications
You must be signed in to change notification settings - Fork 76
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Tensorflow to Barracuda(FusedBatchNormV3) #13
Comments
@Robin2091 any chance you could share your model? It might be with random weights. |
Hey @mantasp ! I have the same problem. IGNORED: FusedBatchNormV3 unknown layer. If you'd like to check download from here for your comfort. |
Thank you! adding it to our issue tracker. |
@Robin2091 @MarkTension I just implemented support for FusedBatchNormV3 and FusedBatchNormV2. Will be shipped with the next release. Meanwhile you could try my fix locally. Just replace Tools/tensorflow_to_barracuda.py with the one in this zip: tensorflow_to_barracuda.py.zip. |
Thank you! @rejunity It seems though that the local fix by itself, combined with the latest barracuda.py file crashes when converting the model.
|
I have a yolov3tiny model in a frozen graph (.pb) file. When I run the tensorflow_to_barracuda.py script I get the following error.
IGNORED: FusedBatchNormV3 unknown layer
Traceback (most recent call last):
File "tensorflow_to_barracuda.py", line 26, in
tf2bc.convert(args.source_file, args.target_file, args.trim_unused_by_output, args)
File "C:\Users\sudes\Documents\barracuda-release\Tools\tensorflow_to_barracuda.py", line 1347, in convert
process_model(i_model, args)
File "C:\Users\sudes\Documents\barracuda-release\Tools\tensorflow_to_barracuda.py", line 1209, in process_model
process_layer(node, o_context, args)
File "C:\Users\sudes\Documents\barracuda-release\Tools\tensorflow_to_barracuda.py", line 1084, in process_layer
assert(all_elements_equal(input_ranks))
AssertionError
Is this because FusedBatchNormv3 is not supported. If not, when will it be?
The text was updated successfully, but these errors were encountered: