MobilenetV2 model error!

[zhangxujinsh]

1: set config.MODEL.net_structure='MobilenetV2' 2: python train.py and get the following info: Failed to create op 0: Op(op=<function convolution2d at 0x7ff585f365f0>, params={'stride': 2, 'num_outputs': 32, 'kernel_size': [3, 3]}, multiplier_func=<function depth_multiplier at 0x7ff56753c170>) params: {'stride': 2, 'num_outputs': 16, 'kernel_size': [3, 3]} Traceback (most recent call last): File "train.py", line 15, in trainner.train() File "/ws/opensource/face/fd/tensorflow_fd/centernet/mobilenetv3_centernet_mnet025/lib/core/base_trainer/net_work.py", line 525, in train self.train_loop() File "/ws/opensource/face/fd/tensorflow_fd/centernet/mobilenetv3_centernet_mnet025/lib/core/base_trainer/net_work.py", line 362, in train_loop self.build() File "/ws/opensource/face/fd/tensorflow_fd/centernet/mobilenetv3_centernet_mnet025/lib/core/base_trainer/network.py", line 265, in build scope, images, hm, wh,weight_, training) File "/ws/opensource/face/fd/tensorflow_fd/centernet/mobilenetv3_centernet_mnet025/lib/core/base_trainer/net_work.py", line 147, in tower_loss hm_loss,wh_loss = centernet.forward(images, kpshm, wh,weights, training) File "/ws/opensource/face/fd/tensorflow_fd/centernet/mobilenetv3_centernet_mnet025/lib/core/model/centernet.py", line 51, in forward origin_fms=self.backbone(inputs,training_flag) File "/ws/opensource/face/fd/tensorflow_fd/centernet/mobilenetv3_centernet_mnet025/lib/core/model/net/mobilenet/backbone.py", line 52, in mobilenetssd ,endpoint = mobilenet_v2_035(image,is_training=is_training,base_only=True,finegrain_classification_mode=False) File "/ws/data/virtualenvs/py379_gw/lib/python3.7/site-packages/tensorflow_core/contrib/framework/python/ops/arg_scope.py", line 182, in func_with_args return func(args, current_args) File "/ws/opensource/face/fd/tensorflow_fd/centernet/mobilenetv3_centernet_mnet025/lib/core/model/net/mobilenet/mobilenet_v2.py", line 157, in mobilenet kwargs) File "/ws/data/virtualenvs/py379_gw/lib/python3.7/site-packages/tensorflow_core/contrib/framework/python/ops/arg_scope.py", line 182, in func_with_args return func(args, current_args) File "/ws/opensource/face/fd/tensorflow_fd/centernet/mobilenetv3_centernet_mnet025/lib/core/model/net/mobilenet/mobilenet.py", line 347, in mobilenet net, end_points = mobilenet_base(inputs, scope=scope, mobilenet_args) File "/ws/data/virtualenvs/py379_gw/lib/python3.7/site-packages/tensorflow_core/contrib/framework/python/ops/arg_scope.py", line 182, in func_with_args return func(args, current_args) File "/ws/opensource/face/fd/tensorflow_fd/centernet/mobilenetv3_centernet_mnet025/lib/core/model/net/mobilenet/mobilenet.py", line 270, in mobilenet_base net = opdef.op(net, params) File "/ws/data/virtualenvs/py379_gw/lib/python3.7/site-packages/tensorflow_core/contrib/framework/python/ops/arg_scope.py", line 182, in func_with_args return func(args, current_args) File "/ws/data/virtualenvs/py379_gw/lib/python3.7/site-packages/tensorflow_core/contrib/layers/python/layers/layers.py", line 1159, in convolution2d conv_dims=2) File "/ws/data/virtualenvs/py379_gw/lib/python3.7/site-packages/tensorflow_core/contrib/framework/python/ops/arg_scope.py", line 182, in func_with_args return func(*args, *current_args) File "/ws/data/virtualenvs/py379_gw/lib/python3.7/site-packages/tensorflow_core/contrib/layers/python/layers/layers.py", line 1057, in convolution outputs = layer.apply(inputs) File "/ws/data/virtualenvs/py379_gw/lib/python3.7/site-packages/tensorflow_core/python/util/deprecation.py", line 324, in new_func return func(args, kwargs) File "/ws/data/virtualenvs/py379_gw/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/base_layer.py", line 1700, in apply return self.call(inputs, *args, *kwargs) File "/ws/data/virtualenvs/py379_gw/lib/python3.7/site-packages/tensorflow_core/python/layers/base.py", line 548, in call outputs = super(Layer, self).call(inputs, args, **kwargs) File "/ws/data/virtualenvs/py379_gw/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/base_layer.py", line 824, in call self._maybe_build(inputs) File "/ws/data/virtualenvs/py379_gw/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/base_layer.py", line 2146, in _maybe_build self.build(input_shapes) File "/ws/data/virtualenvs/py379_gw/lib/python3.7/site-packages/tensorflow_core/python/keras/layers/convolutional.py", line 165, in build dtype=self.dtype) File "/ws/data/virtualenvs/py379_gw/lib/python3.7/site-packages/tensorflow_core/python/layers/base.py", line 466, in add_weight self._handle_weight_regularization(name, variable, regularizer) File "/ws/data/virtualenvs/py379_gw/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/base_layer.py", line 1928, in _handle_weight_regularization self.add_loss(functools.partial(_loss_for_variable, variable)) File "/ws/data/virtualenvs/py379_gw/lib/python3.7/site-packages/tensorflow_core/python/layers/base.py", line 292, in add_loss loss_tensor = regularizer() File "/ws/data/virtualenvs/py379_gw/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/base_layer.py", line 1092, in _tag_unconditional loss = loss() File "/ws/data/virtualenvs/py379_gw/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/base_layer.py", line 1921, in _loss_for_variable regularization = regularizer(v) File "/ws/data/virtualenvs/py379_gw/lib/python3.7/site-packages/tensorflow_core/contrib/layers/python/layers/regularizers.py", line 106, in l2 name='scale') File "/ws/data/virtualenvs/py379_gw/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py", line 1184, in convert_to_tensor return convert_to_tensor_v2(value, dtype, preferred_dtype, name) File "/ws/data/virtualenvs/py379_gw/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py", line 1242, in convert_to_tensor_v2 as_ref=False) File "/ws/data/virtualenvs/py379_gw/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py", line 1273, in internal_convert_to_tensor (dtype.name, value.dtype.name, value))

ValueError: Tensor conversion requested dtype float32 for Tensor with dtype bool: <tf.Tensor 'training_flag:0' shape= dtype=bool>

Could you give me a hint?

[610265158]

Sorry, i am no longer work with tensorflow, so the code is not maintained. Feel really sorry for that.

[zhangxujinsh]

Thanks for your reply! Good luck!