TensorBoard一边学习一边尝试打电话fit_generator
我得到一个错误
InvalidArgumentError: You must feed a value for placeholder tensor 'input_1' with dtype float and shape [?,200,200,3]
[[{{node input_1}} = Placeholder[dtype=DT_FLOAT, shape=[?,200,200,3], _device="/job:localhost/replica:0/task:0/device:GPU:0"]()]]
编码
t_Board = TensorBoard(log_dir= content_drive + 'save/tb_logs', histogram_freq=1, write_images=True)
history = model.fit_generator(
train_generator,
steps_per_epoch = nb_train_samples // batch_size,
epochs = epochs,
validation_data = val_generator,
validation_steps = nb_validation_samples // batch_size,
callbacks = [t_Board ])
keras中的TensorBoard无法运行直方图