Training problem

[233AvavAvA]

after I ran "python model.py > train.txt 2>&1 &!" I got this traceback:

is that caused by keras or numpy version?

building model...

Traceback (most recent call last): File "model.py", line 486, in model = Model() File "model.py", line 65, in init self._build_model() File "model.py", line 78, in _build_model self.generator.build(input_shape=gen_input) File "/root/miniconda3/envs/hmr/lib/python3.8/site-packages/keras/engine/training.py", line 440, in build self.call(x, **kwargs) File "/root/hmr2.0/src/main/generator.py", line 91, in call features = self.resnet50V2(inputs, **kwargs) File "/root/miniconda3/envs/hmr/lib/python3.8/site-packages/keras/utils/traceback_utils.py", line 67, in error_handler raise e.with_traceback(filtered_tb) from None File "/root/miniconda3/envs/hmr/lib/python3.8/site-packages/tensorflow/python/framework/ops.py", line 1939, in _create_c_op raise ValueError(e.message) ValueError: Exception encountered when calling layer "conv2_block1_out" (type Add).

Dimensions must be equal, but are 59 and 61 for '{{node resnet50v2/conv2_block1_out/add}} = AddV2[T=DT_FLOAT](resnet50v2/conv2_block1_0_conv/BiasAdd, resnet50v2/conv2_block1_3_conv/BiasAdd)' with input shapes: [64,59,59,256], [64,61,61,256].

Call arguments received: • inputs=['tf.Tensor(shape=(64, 59, 59, 256), dtype=float32)', 'tf.Tensor(shape=(64, 61, 61, 256), dtype=float32)']