Toybrick

标题: ssd_mobilenet_v2_coco_2018_03_29 转换失败，请帮忙看看为什么？ [打印本页]

作者: linuxsky 时间: 2019-2-15 13:29
标题: ssd_mobilenet_v2_coco_2018_03_29 转换失败，请帮忙看看为什么？
ssd_mobilenet_v2_coco_2018_03_29 下载后调用函数转换失败，附上 log模型下载地址：[color=var(--paper-grey-600)]http://download.tensorflow.org/models/object_detection/ssd_mobilenet_v2_coco_2018_03_29.tar.gz
log：
$ python3 ssd.py
W verbose file path is invalid, debug info will not dump to file.
--> Loading model
D import clients finished
E Catch exception when loading tensorflow model: ./frozen_inference_graph.pb!
T Traceback (most recent call last):
T File "rknn/api/rknn_base.py", line 143, in rknn.api.rknn_base.RKNNBase.load_tensorflow
T File "rknn/base/rknnlib/converter/convert_tf.py", line 93, in rknn.base.rknnlib.converter.convert_tf.convert_tf.__init__
T File "rknn/base/rknnlib/converter/tensorflowloader.py", line 53, in rknn.base.rknnlib.converter.tensorflowloader.TF_Graph_Preprocess.__init__
T AttributeError: 'NoneType' object has no attribute 'op'
done
--> Building model
2019-02-15 13:07:52.052737: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
E Catch exception when building RKNN model!
T Traceback (most recent call last):
T File "rknn/api/rknn_base.py", line 470, in rknn.api.rknn_base.RKNNBase.build
T File "rknn/api/rknn_base.py", line 874, in rknn.api.rknn_base.RKNNBase._quantize
T File "rknn/base/tensorzonex.py", line 213, in rknn.base.tensorzonex.get_data_file
T File "/usr/lib/python3.5/posixpath.py", line 122, in splitext
T    return genericpath._splitext(p, sep, None, extsep)
T File "/usr/lib/python3.5/genericpath.py", line 118, in _splitext
T    sepIndex = p.rfind(sep)
T AttributeError: 'NoneType' object has no attribute 'rfind'
done
--> Init runtime environment
done
--> Running model
E RKNN model is None
done
inference result:  None
Traceback (most recent call last):
  File "ssd.py", line 88, in <module>
predictions = outputs[1].reshape((1, NUM_RESULTS, 4))
TypeError: 'NoneType' object is not subscriptable

作者: linuxsky 时间: 2019-2-15 13:31
ssd_mobilenet_v2_quantized_300x300_coco_2018_09_14 这个也是一样的错误，是 V2 里面一些 OP 不支持么？

作者: yhc 时间: 2019-2-18 12:07
input节点修改一下，和ssd_mobilenet_v1是不一样的

    rknn.load_tensorflow(tf_pb='./ssd_mobilenet_v2_coco_2018_03_29/frozen_inference_graph.pb',

                         inputs=['FeatureExtractor/MobilenetV2/MobilenetV2/input'],

                         outputs=['concat', 'concat_1'],

                         input_size_list=[[INPUT_SIZE, INPUT_SIZE, 3]])
复制代码

作者: linuxsky 时间: 2019-2-18 13:56

yhc 发表于 2019-2-18 12:07
input节点修改一下，和ssd_mobilenet_v1是不一样的

赞，多谢多谢

作者: charles 时间: 2019-4-25 15:18
新手弱弱问下，input，output是怎么确定的？有什么方法？

作者: wujialiang 时间: 2020-2-19 18:06

yhc 发表于 2019-2-18 12:07
input节点修改一下，和ssd_mobilenet_v1是不一样的

请问输入和输入节点名字怎么确定的？能帮忙看看mask_rcnn_resnet50_atrous_coco_2018_01_28这个模型的输入输出节点吗？

作者: zehao 时间: 2021-2-23 16:31

yhc 发表于 2019-2-18 12:07
input节点修改一下，和ssd_mobilenet_v1是不一样的

请问input,output的节点是怎么确认的？

欢迎光临 Toybrick (https://t.rock-chips.com/)