search

Kikyo-16 / Sound_event_detection

This code aims at weakly-labeled semi-supervised sound event detection. The code embraces two methods we proposed to solve this task: specialized decision surface (SDS) and disentangled feature (DF) for weakly-supervised learning and guided learning (GL) for semi-supervised learning. We're so glad if you're interested in using it for research purpose or DCASE participation.
MIT License
125 stars 28 forks source link

Unable to Reproduce DCASE2019 Task4 challenge results #4

Open visionchan opened 2 years ago

visionchan commented 2 years ago

Hi Lin. Here's the error log -

Traceback (most recent call last): File "/home/chenyuanjian/SoundEventDetection/GuidedLearning/main.py", line 326, in test_models(task_name, sed_model_name, model_weights_list) File "/home/chenyuanjian/SoundEventDetection/GuidedLearning/main.py", line 203, in test_models test(task_name, sed_model_name, model_list[0]) File "/home/chenyuanjian/SoundEventDetection/GuidedLearning/main.py", line 150, in test at_preds_out = train.save_at_result(at_preds) #audio tagging result File "/home/chenyuanjian/SoundEventDetection/GuidedLearning/src/trainer.py", line 369, in save_at_result preds_out['vali'] = self.save_at('vali', at_preds, is_add = False) File "/home/chenyuanjian/SoundEventDetection/GuidedLearning/src/trainer.py", line 409, in save_at preds, labels = self.test(mode, 'at', at_preds) File "/home/chenyuanjian/SoundEventDetection/GuidedLearning/src/trainer.py", line 335, in test preds = model.predict(data[0], batch_size = data_loader.batch_size) File "/home/chenyuanjian/anaconda3/envs/dcase2019keras/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py", line 88, in _method_wrapper return method(self, *args, kwargs) File "/home/chenyuanjian/anaconda3/envs/dcase2019keras/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py", line 1268, in predict tmp_batch_outputs = predict_function(iterator) File "/home/chenyuanjian/anaconda3/envs/dcase2019keras/lib/python3.6/site-packages/tensorflow/python/eager/def_function.py", line 580, in call result = self._call(*args, *kwds) File "/home/chenyuanjian/anaconda3/envs/dcase2019keras/lib/python3.6/site-packages/tensorflow/python/eager/def_function.py", line 627, in _call self._initialize(args, kwds, add_initializers_to=initializers) File "/home/chenyuanjian/anaconda3/envs/dcase2019keras/lib/python3.6/site-packages/tensorflow/python/eager/def_function.py", line 506, in _initialize args, kwds)) File "/home/chenyuanjian/anaconda3/envs/dcase2019keras/lib/python3.6/site-packages/tensorflow/python/eager/function.py", line 2446, in _get_concrete_function_internal_garbage_collected graphfunction, , _ = self._maybe_define_function(args, kwargs) File "/home/chenyuanjian/anaconda3/envs/dcase2019keras/lib/python3.6/site-packages/tensorflow/python/eager/function.py", line 2777, in _maybe_define_function graph_function = self._create_graph_function(args, kwargs) File "/home/chenyuanjian/anaconda3/envs/dcase2019keras/lib/python3.6/site-packages/tensorflow/python/eager/function.py", line 2667, in _create_graph_function capture_by_value=self._capture_by_value), File "/home/chenyuanjian/anaconda3/envs/dcase2019keras/lib/python3.6/site-packages/tensorflow/python/framework/func_graph.py", line 981, in func_graph_from_py_func func_outputs = python_func(*func_args, *func_kwargs) File "/home/chenyuanjian/anaconda3/envs/dcase2019keras/lib/python3.6/site-packages/tensorflow/python/eager/def_function.py", line 441, in wrapped_fn return weak_wrapped_fn().wrapped(args, **kwds) File "/home/chenyuanjian/anaconda3/envs/dcase2019keras/lib/python3.6/site-packages/tensorflow/python/framework/func_graph.py", line 968, in wrapper raise e.ag_error_metadata.to_exception(e) ValueError: in user code:

/home/chenyuanjian/anaconda3/envs/dcase2019keras/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py:1147 predict_function  *
    outputs = self.distribute_strategy.run(
/home/chenyuanjian/SoundEventDetection/GuidedLearning/src/model.py:50 call  *
    weights = K.sum(inputs * self.kernel, axis = -1) + self.bias
/home/chenyuanjian/anaconda3/envs/dcase2019keras/lib/python3.6/site-packages/tensorflow/python/ops/math_ops.py:997 binary_op_wrapper
    return func(x, y, name=name)
/home/chenyuanjian/anaconda3/envs/dcase2019keras/lib/python3.6/site-packages/tensorflow/python/ops/math_ops.py:1283 _mul_dispatch
    return gen_math_ops.mul(x, y, name=name)
/home/chenyuanjian/anaconda3/envs/dcase2019keras/lib/python3.6/site-packages/tensorflow/python/ops/gen_math_ops.py:6092 mul
    "Mul", x=x, y=y, name=name)
/home/chenyuanjian/anaconda3/envs/dcase2019keras/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py:744 _apply_op_helper
    attrs=attr_protos, op_def=op_def)
/home/chenyuanjian/anaconda3/envs/dcase2019keras/lib/python3.6/site-packages/tensorflow/python/framework/func_graph.py:595 _create_op_internal
    compute_device)
/home/chenyuanjian/anaconda3/envs/dcase2019keras/lib/python3.6/site-packages/tensorflow/python/framework/ops.py:3327 _create_op_internal
    op_def=op_def)
/home/chenyuanjian/anaconda3/envs/dcase2019keras/lib/python3.6/site-packages/tensorflow/python/framework/ops.py:1817 __init__
    control_input_ops, op_def)
/home/chenyuanjian/anaconda3/envs/dcase2019keras/lib/python3.6/site-packages/tensorflow/python/framework/ops.py:1657 _create_c_op
    raise ValueError(str(e))

ValueError: Dimensions must be equal, but are 113 and 30 for '{{node model/sed_with_cATP-DF_atten_8/mul}} = Mul[T=DT_FLOAT](model/lambda_16/strided_slice, model/sed_with_cATP-DF_atten_8/mul/ReadVariableOp)' with input shapes: [64,500,113], [1,1,30].
visionchan commented 2 years ago

This means the dimension is not fit？