Tensorflow tf.dataset、多路径输入和每批加载图像的映射

我正在加载一个包含多个输入图像的数据集。输入图像路径应仅在批处理时解码，以便处理大型数据集

数据集是N图像路径输入和M浮点输出。每个输入的图像具有不同的分辨率

Data is ([img_input_1.png, img_input_2.png, ...], [0.65, 0.7, 0.8])

该模型以符号模式使用Keras函数api

这是最近编辑的代码

from itertools import zip_longest

def read_image(path, shape):
    try:
        image = tf.io.read_file(path)
        image = tf.image.decode_png(image)
        image = tf.image.resize(image, [shape[1],shape[2]])
        image /= 255.0
        return image
    except:
        print('ERROR: preprocess_image: bad path', path)    

def load_image(x, y, shp):
    pout = [(k, x[k]) for k in x.keys()]
    l1   = tf.convert_to_tensor(list(x))
    l2   = tf.convert_to_tensor(list(x.values()))

    pl = tf.map_fn(
        lambda args: (read_image(args[0], shp), args[1]), [l1, l2], dtype=(tf.float32, tf.float32)
    )
    pl = {path: (pl[0][i], pl[1][i]) for i, path in enumerate(x)}
    return (pl,y)

def dataset_prep(json_data, seq, batch_size):
    # LOAD DATA FROM JSON
    x,y = json_parse_x_y(json_data[seq])
    xx  = [*zip_longest(*x)] # NOTE: goes from variable sized input to {'input_N':...}
    yy  = [*zip_longest(*y)]

    # GET SHAPES (hard coded atm)
    lns = [[len(xxx)] for xxx in xx]
    rzs = [[24,512,1],[96,512,1]] # TEMP TODO! grab grom [(v['h'],v['w'],v['c']) for v in xx]
    shp = [*zip_longest(*[lns,rzs])]
    shp = [list(s) for s in shp]
    shp = [[*itertools.chain.from_iterable(s)] for s in shp]

    xd  = dict([[ "input_{}".format(i+1),np.array(y)] for i,y in [*enumerate(xx)]])
    yd  = dict([["output_{}".format(i+1),np.array(y)] for i,y in [*enumerate(yy)]])

    ds  = tf.data.Dataset.from_tensor_slices((xd, yd))

    ds  = ds.shuffle(10000)
    ds  = ds.repeat()
    ds  = ds.map(map_func=lambda x,y: load_image(x, y, shp), num_parallel_calls=AUTOTUNE)
    ds  = ds.batch(batch_size) if batch_size else ds 
    ds  = ds.prefetch(AUTOTUNE) 
    return ds

这就是我得到的错误：

Traceback (most recent call last):
    File "/home/me/.local/bin/wavfeat", line 11, in <module>
        load_entry_point('wavfeat==0.1.0', 'console_scripts', 'wavfeat')()
    File "/home/me/.local/lib/python3.6/site-packages/wavfeat/__main__.py", line 91, in main
        analysis_batch_sql(obj)
    File "/home/me/.local/lib/python3.6/site-packages/wavfeat/analysis_run_csv.py", line 50, in analysis_batch_sql
        qy = [*map(lambda c: run_elm(c[0], c[1]), ch)]
    File "/home/me/.local/lib/python3.6/site-packages/wavfeat/analysis_run_csv.py", line 50, in <lambda>
        qy = [*map(lambda c: run_elm(c[0], c[1]), ch)]
    File "/home/me/.local/lib/python3.6/site-packages/wavfeat/analysis_run_csv.py", line 23, in run_elm
        out = fn(input, elm)
    File "/home/me/.local/lib/python3.6/site-packages/wavfeat/one_sec_onset.py", line 196, in one_sec_onset_train
        return train(input, elm)
    File "/home/me/.local/lib/python3.6/site-packages/wavfeat/one_sec_onset.py", line 182, in train
        ts = dataset_prep(jd, 'train', bc)
    File "/home/me/.local/lib/python3.6/site-packages/wavfeat/one_sec_onset.py", line 123, in dataset_prep
        ds  = ds.map(map_func=lambda x,y: load_image(x, y, shp), num_parallel_calls=AUTOTUNE)
    File "/home/me/.local/lib/python3.6/site-packages/tensorflow/python/data/ops/dataset_ops.py", line 1146, in map
        self, map_func, num_parallel_calls, preserve_cardinality=True)
    File "/home/me/.local/lib/python3.6/site-packages/tensorflow/python/data/ops/dataset_ops.py", line 3264, in __init__
        use_legacy_function=use_legacy_function)
    File "/home/me/.local/lib/python3.6/site-packages/tensorflow/python/data/ops/dataset_ops.py", line 2591, in __init__
        self._function = wrapper_fn._get_concrete_function_internal()
    File "/home/me/.local/lib/python3.6/site-packages/tensorflow/python/eager/function.py", line 1366, in _get_concrete_function_internal
        *args, **kwargs)
    File "/home/me/.local/lib/python3.6/site-packages/tensorflow/python/eager/function.py", line 1360, in _get_concrete_function_internal_garbage_collected
        graph_function, _, _ = self._maybe_define_function(args, kwargs)
    File "/home/me/.local/lib/python3.6/site-packages/tensorflow/python/eager/function.py", line 1648, in _maybe_define_function
        graph_function = self._create_graph_function(args, kwargs)
    File "/home/me/.local/lib/python3.6/site-packages/tensorflow/python/eager/function.py", line 1541, in _create_graph_function
        capture_by_value=self._capture_by_value),
    File "/home/me/.local/lib/python3.6/site-packages/tensorflow/python/framework/func_graph.py", line 716, in func_graph_from_py_func
        func_outputs = python_func(*func_args, **func_kwargs)
    File "/home/me/.local/lib/python3.6/site-packages/tensorflow/python/data/ops/dataset_ops.py", line 2585, in wrapper_fn
        ret = _wrapper_helper(*args)
    File "/home/me/.local/lib/python3.6/site-packages/tensorflow/python/data/ops/dataset_ops.py", line 2530, in _wrapper_helper
        ret = func(*nested_args)
    File "/home/me/.local/lib/python3.6/site-packages/wavfeat/one_sec_onset.py", line 123, in <lambda>
        ds  = ds.map(map_func=lambda x,y: load_image(x, y, shp), num_parallel_calls=AUTOTUNE)
    File "/home/me/.local/lib/python3.6/site-packages/wavfeat/one_sec_data_loader.py", line 91, in load_image
        print("x['input_1'].values(): ", x['input_1'].values())
AttributeError: 'Tensor' object has no attribute 'values'

编辑2

尝试最新版本时，出现以下错误

Traceback (most recent call last):
  File "/home/me/.local/bin/wavfeat", line 11, in <module>
    load_entry_point('wavfeat==0.1.0', 'console_scripts', 'wavfeat')()
  File "/home/me/.local/lib/python3.6/site-packages/wavfeat/__main__.py", line 91, in main
    analysis_batch_sql(obj)
  File "/home/me/.local/lib/python3.6/site-packages/wavfeat/analysis_run_csv.py", line 50, in analysis_batch_sql
    qy = [*map(lambda c: run_elm(c[0], c[1]), ch)]
  File "/home/me/.local/lib/python3.6/site-packages/wavfeat/analysis_run_csv.py", line 50, in <lambda>
    qy = [*map(lambda c: run_elm(c[0], c[1]), ch)]
  File "/home/me/.local/lib/python3.6/site-packages/wavfeat/analysis_run_csv.py", line 23, in run_elm
    out = fn(input, elm)
  File "/home/me/.local/lib/python3.6/site-packages/wavfeat/one_sec_onset.py", line 216, in one_sec_onset_train
    return train(input, elm)
  File "/home/me/.local/lib/python3.6/site-packages/wavfeat/one_sec_onset.py", line 203, in train
    vs = validation_prep(jd, 'validation', bc)
  File "/home/me/.local/lib/python3.6/site-packages/wavfeat/one_sec_onset.py", line 176, in validation_prep
    ds  = ds.map(map_func=load_and_preprocess_from_path_label, num_parallel_calls=AUTOTUNE)
  File "/home/me/.local/lib/python3.6/site-packages/tensorflow/python/data/ops/dataset_ops.py", line 1146, in map
    self, map_func, num_parallel_calls, preserve_cardinality=True)
  File "/home/me/.local/lib/python3.6/site-packages/tensorflow/python/data/ops/dataset_ops.py", line 3264, in __init__
    use_legacy_function=use_legacy_function)
  File "/home/me/.local/lib/python3.6/site-packages/tensorflow/python/data/ops/dataset_ops.py", line 2591, in __init__
    self._function = wrapper_fn._get_concrete_function_internal()
  File "/home/me/.local/lib/python3.6/site-packages/tensorflow/python/eager/function.py", line 1366, in _get_concrete_function_internal
    *args, **kwargs)
  File "/home/me/.local/lib/python3.6/site-packages/tensorflow/python/eager/function.py", line 1360, in _get_concrete_function_internal_garbage_collected
    graph_function, _, _ = self._maybe_define_function(args, kwargs)
  File "/home/me/.local/lib/python3.6/site-packages/tensorflow/python/eager/function.py", line 1648, in _maybe_define_function
    graph_function = self._create_graph_function(args, kwargs)
  File "/home/me/.local/lib/python3.6/site-packages/tensorflow/python/eager/function.py", line 1541, in _create_graph_function
    capture_by_value=self._capture_by_value),
  File "/home/me/.local/lib/python3.6/site-packages/tensorflow/python/framework/func_graph.py", line 716, in func_graph_from_py_func
    func_outputs = python_func(*func_args, **func_kwargs)
  File "/home/me/.local/lib/python3.6/site-packages/tensorflow/python/data/ops/dataset_ops.py", line 2585, in wrapper_fn
    ret = _wrapper_helper(*args)
  File "/home/me/.local/lib/python3.6/site-packages/tensorflow/python/data/ops/dataset_ops.py", line 2530, in _wrapper_helper
    ret = func(*nested_args)
  File "/home/me/.local/lib/python3.6/site-packages/wavfeat/one_sec_data_loader.py", line 47, in load_and_preprocess_from_path_label
    pl   = dict([(pk, tf.map_fn(load_and_preprocess_image, po, dtype=tf.float32)) for pk,po in pout])
  File "/home/me/.local/lib/python3.6/site-packages/wavfeat/one_sec_data_loader.py", line 47, in <listcomp>
    pl   = dict([(pk, tf.map_fn(load_and_preprocess_image, po, dtype=tf.float32)) for pk,po in pout])
  File "/home/me/.local/lib/python3.6/site-packages/tensorflow/python/ops/map_fn.py", line 214, in map_fn
    raise ValueError("elems must be a 1+ dimensional Tensor, not a scalar")
ValueError: elems must be a 1+ dimensional Tensor, not a scalar

回溯（最近一次呼叫最后一次）：
文件“/home/me/.local/bin/wavfeat”，第11行，在
加载入口点（'wavfeat==0.1.0'，'console\u scripts'，'wavfeat'）（）
文件“/home/me/.local/lib/python3.6/site packages/wavfeat/\uuuuuuu main\uuuuuuuuuu.py”，第91行，在main中
分析\批处理\ sql（obj）
文件“/home/me/.local/lib/python3.6/site packages/wavfeat/analysis\u run\u csv.py”，第50行，在analysis\u batch\u sql中
qy=[*map（lambda c:run_elm（c[0]，c[1]），ch）]
文件“/home/me/.local/lib/python3.6/site packages/wavfeat/analysis\u run\u csv.py”，第50行，在
qy=[*map（lambda c:run_elm（c[0]，c[1]），ch）]
文件“/home/me/.local/lib/python3.6/site packages/wavfeat/analysis\u run\u csv.py”，第23行，在run\u elm中
输出=fn（输入，elm）
文件“/home/me/.local/lib/python3.6/site packages/wavfeat/one_sec_start.py”，第216行，在one_sec_start_列中
返回列车（输入，elm）
文件“/home/me/.local/lib/python3.6/site packages/wavfeat/one_sec_start.py”，第203行，列车中
vs=验证准备（jd，“验证”，bc）
文件“/home/me/.local/lib/python3.6/site packages/wavfeat/one_sec_start.py”，第176行，在验证准备中
ds=ds.map（map\u func=load\u和\u preprocess\u来自\u path\u标签，num\u parallel\u calls=AUTOTUNE）
文件“/home/me/.local/lib/python3.6/site packages/tensorflow/python/data/ops/dataset_ops.py”，地图中的第1146行
self、map\u func、num\u parallel\u调用、preserve\u cardinality=True）
文件“/home/me/.local/lib/python3.6/site packages/tensorflow/python/data/ops/dataset_ops.py”，第3264行，在u init中__
使用旧功能=使用旧功能）
文件“/home/me/.local/lib/python3.6/site packages/tensorflow/python/data/ops/dataset_ops.py”，第2591行，在u init中__
self.\u function=wrapper\u fn.\u get\u concrete\u function\u internal（）
文件“/home/me/.local/lib/python3.6/site-packages/tensorflow/python/eager/function.py”，第1366行，在内部获取具体函数
*args，**kwargs）
文件“/home/me/.local/lib/python3.6/site packages/tensorflow/python/eager/function.py”，第1360行，位于“获取”\u具体\u函数\u内部\u垃圾收集”
图函数，自我，可能定义函数（args，kwargs）
文件“/home/me/.local/lib/python3.6/site packages/tensorflow/python/eager/function.py”，第1648行，在函数定义中
graph\u function=self.\u create\u graph\u function（args，kwargs）
文件“/home/me/.local/lib/python3.6/site packages/tensorflow/python/eager/function.py”，第1541行，在创建图形函数中
按值捕获=自身。_按值捕获），
文件“/home/me/.local/lib/python3.6/site-packages/tensorflow/python/framework/func_-graph.py”，第716行，在func_-graph_中，从_-py_-func开始
func_outputs=python_func（*func_args，**func_kwargs）
文件“/home/me/.local/lib/python3.6/site packages/tensorflow/python/data/ops/dataset_ops.py”，第2585行，在wrapper_fn中
ret=\u包装器\u帮助器（*args）
文件“/home/me/.local/lib/python3.6/site packages/tensorflow/python/data/ops/dataset_ops.py”，第2530行，在_wrapper_helper中
ret=func（*嵌套参数）
文件“/home/me/.local/lib/python3.6/site packages/wavfeat/one_sec_data_loader.py”，第47行，从路径标签加载和预处理
pl=dict（[（pk，tf.map\u fn（加载和预处理图像，po，dtype=tf.float32））用于pk，po在pout中]）
文件“/home/me/.local/lib/python3.6/site packages/wavfeat/one_sec_data_loader.py”，第47行，在
pl=dict（[（pk，tf.map\u fn（加载和预处理图像，po，dtype=tf.float32））用于pk，po在pout中]）
文件“/home/me/.local/lib/python3.6/site packages/tensorflow/python/ops/map\u fn.py”，第214行，在map\u fn中
raise VALUERROR（“元素必须是1+维张量，而不是标量”）
ValueError：元素必须是1+维张量，而不是标量

加载项：不使用dict结构 这是一个完整的代码（除了定义

json\u parse\u x\u y

和声明

AUTOTUNE

）来实现您在不使用dict结构的情况下尝试的功能

我测试了

make_dataset

的工作原理（参见下面的示例），因此如果遇到问题，应该是由于有关

load_张量的规范错误引起的

从itertools导入zip\u
导入tensorflow作为tf
#此外，必须定义'json_parse_x_y'
#并且必须声明'AUTOTUNE'（在我的示例中，我将其设置为2）
def读取图像（路径、形状）：
“”“读取给定文件路径和张量形状的图像。
返回给定形状的浮点张量。
"""
尝试：
image=tf.io.read\u文件（路径）
image=tf.image.decode\u png（图像）
image=tf.image.resize（图像，[shape[1]，shape[2]]）
图像/=255.0
返回图像
除：
raise FileNotFoundError（“预处理\u映像：错误路径“%s”%”%path）
def load_图像（路径、形状）：
“”“加载图像集合（与单个样本关联）。
路径：秩1字符串张量
形状：图像形状列表（与“路径”长度相同）
返回包含加载图像的浮点张量元组。
"""
返回元组((
读取图像（路径[i]，形状[i]）
适用于范围内的i（透镜（形状））
))
def load_张量（json_数据，序号）：
“”“从json转储加载图像描述符。
返回包含以下内容的元组：
*包含映像路径列表的秩2张量（str）
*包含分辨率值的秩2张量（浮点）
*图像形状列表，长度与秩2相同
张量第二轴
"""
x、 y=json_parse_x_y（json_d
  File "/home/me/.local/lib/python3.6/site-packages/tensorflow/python/framework/constant_op.py", line 284, in _constant_impl
    allow_broadcast=allow_broadcast))
  File "/home/me/.local/lib/python3.6/site-packages/tensorflow/python/framework/tensor_util.py", line 455, in make_tensor_proto
    raise ValueError("None values not supported.")
ValueError: None values not supported.


Traceback (most recent call last):
  File "/home/me/.local/bin/wavfeat", line 11, in <module>
    load_entry_point('wavfeat==0.1.0', 'console_scripts', 'wavfeat')()
  File "/home/me/.local/lib/python3.6/site-packages/wavfeat/__main__.py", line 91, in main
    analysis_batch_sql(obj)
  File "/home/me/.local/lib/python3.6/site-packages/wavfeat/analysis_run_csv.py", line 50, in analysis_batch_sql
    qy = [*map(lambda c: run_elm(c[0], c[1]), ch)]
  File "/home/me/.local/lib/python3.6/site-packages/wavfeat/analysis_run_csv.py", line 50, in <lambda>
    qy = [*map(lambda c: run_elm(c[0], c[1]), ch)]
  File "/home/me/.local/lib/python3.6/site-packages/wavfeat/analysis_run_csv.py", line 23, in run_elm
    out = fn(input, elm)
  File "/home/me/.local/lib/python3.6/site-packages/wavfeat/one_sec_onset.py", line 216, in one_sec_onset_train
    return train(input, elm)
  File "/home/me/.local/lib/python3.6/site-packages/wavfeat/one_sec_onset.py", line 203, in train
    vs = validation_prep(jd, 'validation', bc)
  File "/home/me/.local/lib/python3.6/site-packages/wavfeat/one_sec_onset.py", line 176, in validation_prep
    ds  = ds.map(map_func=load_and_preprocess_from_path_label, num_parallel_calls=AUTOTUNE)
  File "/home/me/.local/lib/python3.6/site-packages/tensorflow/python/data/ops/dataset_ops.py", line 1146, in map
    self, map_func, num_parallel_calls, preserve_cardinality=True)
  File "/home/me/.local/lib/python3.6/site-packages/tensorflow/python/data/ops/dataset_ops.py", line 3264, in __init__
    use_legacy_function=use_legacy_function)
  File "/home/me/.local/lib/python3.6/site-packages/tensorflow/python/data/ops/dataset_ops.py", line 2591, in __init__
    self._function = wrapper_fn._get_concrete_function_internal()
  File "/home/me/.local/lib/python3.6/site-packages/tensorflow/python/eager/function.py", line 1366, in _get_concrete_function_internal
    *args, **kwargs)
  File "/home/me/.local/lib/python3.6/site-packages/tensorflow/python/eager/function.py", line 1360, in _get_concrete_function_internal_garbage_collected
    graph_function, _, _ = self._maybe_define_function(args, kwargs)
  File "/home/me/.local/lib/python3.6/site-packages/tensorflow/python/eager/function.py", line 1648, in _maybe_define_function
    graph_function = self._create_graph_function(args, kwargs)
  File "/home/me/.local/lib/python3.6/site-packages/tensorflow/python/eager/function.py", line 1541, in _create_graph_function
    capture_by_value=self._capture_by_value),
  File "/home/me/.local/lib/python3.6/site-packages/tensorflow/python/framework/func_graph.py", line 716, in func_graph_from_py_func
    func_outputs = python_func(*func_args, **func_kwargs)
  File "/home/me/.local/lib/python3.6/site-packages/tensorflow/python/data/ops/dataset_ops.py", line 2585, in wrapper_fn
    ret = _wrapper_helper(*args)
  File "/home/me/.local/lib/python3.6/site-packages/tensorflow/python/data/ops/dataset_ops.py", line 2530, in _wrapper_helper
    ret = func(*nested_args)
  File "/home/me/.local/lib/python3.6/site-packages/wavfeat/one_sec_data_loader.py", line 47, in load_and_preprocess_from_path_label
    pl   = dict([(pk, tf.map_fn(load_and_preprocess_image, po, dtype=tf.float32)) for pk,po in pout])
  File "/home/me/.local/lib/python3.6/site-packages/wavfeat/one_sec_data_loader.py", line 47, in <listcomp>
    pl   = dict([(pk, tf.map_fn(load_and_preprocess_image, po, dtype=tf.float32)) for pk,po in pout])
  File "/home/me/.local/lib/python3.6/site-packages/tensorflow/python/ops/map_fn.py", line 214, in map_fn
    raise ValueError("elems must be a 1+ dimensional Tensor, not a scalar")
ValueError: elems must be a 1+ dimensional Tensor, not a scalar