Closed peterpaniff closed 5 years ago
i follow the instrctions. The code below was added to example/ssd/symbol/symbol_factory.py elif network == 'mobilenet_v2': image_shape = '3,224,224' network = 'mobilenet_v2' from_layers = ['relu6_1_expand', 'relu6_4', '', '', '', ''] num_filters = [-1, -1, 512, 256, 256, 128] strides = [-1, -1, 2, 2, 2, 2] pads = [-1, -1, 1, 1, 1, 1] sizes = [[.1, .141], [.2, .272], [.37, .447], [.54, .619], [.71, .79], [.88, .961]] ratios = [[1, 2, .5], [1, 2, .5, 3, 1. / 3], [1, 2, .5, 3, 1. / 3], [1, 2, .5, 3, 1. / 3], \ [1, 2, .5], [1, 2, .5]] normalizations = -1 steps = [] return locals() when i train the model, but i enconter the error below: TypeError: get_symbol() got an unexpected keyword argument 'image_shape'
i solve it myself
peterpaniff
commented
5 years ago
i follow the instrctions. The code below was added to example/ssd/symbol/symbol_factory.py elif network == 'mobilenet_v2': image_shape = '3,224,224' network = 'mobilenet_v2' from_layers = ['relu6_1_expand', 'relu6_4', '', '', '', ''] num_filters = [-1, -1, 512, 256, 256, 128] strides = [-1, -1, 2, 2, 2, 2] pads = [-1, -1, 1, 1, 1, 1] sizes = [[.1, .141], [.2, .272], [.37, .447], [.54, .619], [.71, .79], [.88, .961]] ratios = [[1, 2, .5], [1, 2, .5, 3, 1. / 3], [1, 2, .5, 3, 1. / 3], [1, 2, .5, 3, 1. / 3], \ [1, 2, .5], [1, 2, .5]] normalizations = -1 steps = [] return locals() when i train the model, but i enconter the error below: TypeError: get_symbol() got an unexpected keyword argument 'image_shape'