deep-learning - Keras fit_generator 验证数据类型错误 : 'float' object cannot be interpreted as an integer

Question

我正在尝试通过 Ning-Ding 运行 CUHK03 Person Re-ID 脚本(使用 Keras 实现 Ahmed 等人的论文)
见 https://github.com/Ning-Ding/Implementation-CVPR2015-CNN-for-ReID

错误文本如下:

TypeError Traceback (most recent call last)
in ()

    ----> 1 main("E:\DL\cuhk-03.h5")

in main(dataset_path)

    17 model = generate_model()
    18 model = compile_model(model)
    ---> 19 train(model, dataset_path)
    20
    21 def train(model,

in train(model, h5_path, weights_name, train_num, one_epoch, epoch_num, flag_random, random_pattern, flag_train, flag_val, which_val_data, nb_val_samples)
    39 rand_x = np.random.rand()
    40 flag_train = random_pattern(rand_x)
    ---> 41 model.fit_generator(Data_Generator.flow(f,flag = flag_train),one_epoch,epoch_num,validation_data=Data_Generator.flow(f,train_or_validation=which_val_data,flag=flag_val),nb_val_samples=nb_val_samples)
    42 Rank1s.append(round(cmc(model)[0],2))
    43 print (Rank1s)

~\Anaconda3\lib\site-packages\keras\legacy\interfaces.py in wrapper(*args, **kwargs)

    89 warnings.warn('Update your ' + object_name + 90 ' call to the Keras 2 API: ' + signature, stacklevel=2)
    ---> 91 return func(*args, **kwargs)
    92 wrapper._original_function = func
    93 return wrapper

~\Anaconda3\lib\site-packages\keras\engine\training.py in fit_generator(self, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)

    2023 epoch = initial_epoch
    2024
    -> 2025 do_validation = bool(validation_data)
    2026 self._make_train_function()
    2027 if do_validation:

TypeError: 'float' object cannot be interpreted as an integer

我在 Windows 10(x86) 上的 Anaconda 中使用 Jupyter Notebook。
Keras 2.1.3 版
Python 版本 3.6.3
Tensorflow 后端 (1.4.0)

Answer 1

好的，这样 validation_data是一个由返回的生成器

Data_Generator.flow(f,train_or_validation=which_val_data,flag=flag_val)

当 do_validation = bool(validation_data)被执行，对对象调用 bool 将调用 nonzero或 len如果定义了其中任何一个。在这种情况下， Sequence工具 len所以它会检查 if len(Sequence) == 0 .您的问题是 len返回 float (这是一个错误)所以当它试图在 bool 中转换它时， 它失败。

断言 len返回 int .

归功于 https://www.bountysource.com/issues/54744813-fit_generator-throws-error-on-validation-data-being-float-data-type 的 Dref360