人工智能开发系列(1) 中文手势识别例程

显示全部楼层 · 发表于 2020-2-18 21:42:35

本帖最后由 ddcat1991 于 2020-2-18 21:46 编辑

你好，我在设置 do_quantization=True 转换上述手势识别的pb模型的时候, 产生如下错误。 (如果使用do_quantization=False时没有错误提示，并且能顺利生成rknn模型).

使用的版本：
* Debian10
* tf 1.14.0
* rknn 1.3.0

Please use `rate` instead of `keep_prob`. Rate should be set to `rate = 1 - keep_prob`.

E Catch exception when building RKNN model!

E Traceback (most recent call last):

E   File "rknn/api/rknn_base.py", line 737, in rknn.api.rknn_base.RKNNBase.build

E   File "rknn/api/rknn_base.py", line 1644, in rknn.api.rknn_base.RKNNBase._quantize2

E   File "rknn/base/RKNNlib/app/medusa/quantization.py", line 105, in rknn.base.RKNNlib.app.medusa.quantization.Quantization.run

E   File "rknn/base/RKNNlib/app/medusa/quantization.py", line 44, in rknn.base.RKNNlib.app.medusa.quantization.Quantization._run_quantization

E   File "rknn/base/RKNNlib/app/medusa/workspace.py", line 129, in rknn.base.RKNNlib.app.medusa.workspace.Workspace.run

E   File "rknn/base/RKNNlib/app/medusa/workspace.py", line 99, in rknn.base.RKNNlib.app.medusa.workspace.Workspace._setup_graph

E   File "rknn/base/RKNNlib/app/medusa/workspace.py", line 100, in rknn.base.RKNNlib.app.medusa.workspace.Workspace._setup_graph

E   File "rknn/base/RKNNlib/RKNNnetbuilder.py", line 274, in rknn.base.RKNNlib.RKNNnetbuilder.RKNNNetBuilder.build

E   File "rknn/base/RKNNlib/RKNNnetbuilder.py", line 278, in rknn.base.RKNNlib.RKNNnetbuilder.RKNNNetBuilder.build

E   File "rknn/base/RKNNlib/RKNNnetbuilder.py", line 305, in rknn.base.RKNNlib.RKNNnetbuilder.RKNNNetBuilder.build_layer

E   File "rknn/base/RKNNlib/RKNNnetbuilder.py", line 305, in rknn.base.RKNNlib.RKNNnetbuilder.RKNNNetBuilder.build_layer

E   File "rknn/base/RKNNlib/RKNNnetbuilder.py", line 305, in rknn.base.RKNNlib.RKNNnetbuilder.RKNNNetBuilder.build_layer

E   File "rknn/base/RKNNlib/RKNNnetbuilder.py", line 331, in rknn.base.RKNNlib.RKNNnetbuilder.RKNNNetBuilder.build_layer

E   File "rknn/base/RKNNlib/RKNNnetbuilder.py", line 336, in rknn.base.RKNNlib.RKNNnetbuilder.RKNNNetBuilder.build_layer

E   File "rknn/base/RKNNlib/layer/RKNNlayer.py", line 287, in rknn.base.RKNNlib.layer.RKNNlayer.RKNNLayer.compute_tensor

E   File "rknn/base/RKNNlib/layer/dropout.py", line 20, in rknn.base.RKNNlib.layer.dropout.Dropout.compute_out_tensor

E   File "/home/toybrick/.local/lib/python3.7/site-packages/tensorflow/python/util/deprecation.py", line 507, in new_func

E     return func(*args, **kwargs)

E   File "/home/toybrick/.local/lib/python3.7/site-packages/tensorflow/python/ops/nn_ops.py", line 4170, in dropout

E     return dropout_v2(x, rate, noise_shape=noise_shape, seed=seed, name=name)

E   File "/home/toybrick/.local/lib/python3.7/site-packages/tensorflow/python/ops/nn_ops.py", line 4219, in dropout_v2

E     "range [0, 1), got %g" % rate)

E ValueError: rate must be a scalar tensor or a float in the range [0, 1), got 1

--> Building model

复制代码

代码如下：

from rknn.api import RKNN



INPUT_SIZE = 64



if __name__ == '__main__':

    model_file_path = '../digital_gesture_recognition/model_2500/digital_gesture.pb'

    

    rknn = RKNN()

    

    print("--> Init rknn enviroment")

    

    # ret = rknn.init_runtime()

    

    rknn.load_tensorflow(tf_pb=model_file_path,

                     inputs=['input_x'],

                     outputs=['probability'],

                     input_size_list=[[INPUT_SIZE, INPUT_SIZE, 3]])

    print("--> Model Loaded")

    

    rknn.config(channel_mean_value='0 0 0 255', reorder_channel='0 1 2')

    print("--> Init config")

    

    rknn.build(do_quantization=True, dataset='./dataset_64x64.txt')

    # rknn.build(do_quantization=False)

    print('--> Building model')

    

    rknn.export_rknn('./digital_gesture.rknn')

    rknn.release()

    

    print('Done')
复制代码

请问这个调用tf的droput_v2报错的问题应该怎么解决？