Error while running demo.py

[shrybht]

Hi,

I'm facing the error: UnimplementedError (see above for traceback): Generic conv implementation only s upports NHWC tensor format for now. [[Node: detector/darknet-53/Conv/Conv2D = Conv2D[T=DT_FLOAT, data_forma t="NCHW", dilations=[1, 1, 1, 1], padding="SAME", strides=[1, 1, 1, 1], use_cudn n_on_gpu=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"](detector/ transpose, ArithmeticOptimizer/detector/darknet-53/Conv/weights_scaled_detector/ darknet-53/Conv/Conv2D)]]

Could you please tell me how to solve the error and run the detector on CPU?

[hc625ma]

Got the same error. Tried changing the format to NHWC in demo.py, but no difference. Would you please kindly point us to where to look at? =)

[corlov]

I have the same problem.

[shrybht]

@mystic123 please help us out.

[anhminh3105]

having the same issue as well.

[camilo912]

You need the parameter --data_format NHWC when you call convert_weights_pb.py and also when you call demo.py for running the demo on CPU.

[corlov]

camilo912, thank you a lot! The code works wonderfully! I have run it so:

python3 ./convert_weights.py --data_format NHWC
python3 ./convert_weights_pb.py --data_format NHWC
python3 demo.py --data_format NHWC --frozen_model frozen_darknet_yolov3_model.pb --input_img img2.jpg --output_img out2.jpg

All significant and large objects were found and processed.