ZengyuanYu

How to get the mask area ?

11

I trained my own data use Mask RCNN。Now, I want to calculate mask area through pixel. How to do that?

Failed to generate pt model

1

It's a really great study，but i want to generate pt and use Netron visualization，display as this： Please help answer this question，thx。 

Train my own dataset?

1

Now I have some pictures, but how i create label(labelme?) ? And then how I train this datasets?

Error Code 4: Miscellaneous (IElementWiseLayer StatefulPartitionedCall/fpn_cells/cell_0/fnode0/add_n/add: broadcast dimensions must be conformable)

2

/usr/src/tensorrt/bin/trtexec --onnx= models/efficidet/efficientdet-lite0/efficientdet-lite0-bs1.onnx --explicitBatch --int8 --workspace=1024 --sparsity=enable

why my loss always keep in 300 and acc under in 50%?

4

苏AZ3A25 1.0 苏AZ3A25 1.0 苏AJ3H16 1.0 苏AJ3H16 1.0 苏AC0378 1.0 苏AS0377 1.0 苏AY9L95 1.0 苏AX9L15 1.0 苏AZ1W57 1.0 苏AZ7X17 1.0 苏AR3595 1.0 苏AR0195 1.0 苏AI0P50 1.0 苏AI0P59 1.0 苏AE8J34 1.0...

code: def read_data(img_glob): for fname in sorted(glob.glob(img_glob)): # fname = fname.decode('utf-8') # fname = fname.encode('utf-8') im = cv2.imread(fname)[:, :, 0].astype(numpy.float32) / 255. code = fname.split("/")[1][9:16] p = fname.split("/")[1][17] == '1'...