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
  1.     rknn.load_tensorflow(tf_pb='./ssd_mobilenet_v2_coco_2018_03_29/frozen_inference_graph.pb',
  2.                          inputs=['FeatureExtractor/MobilenetV2/MobilenetV2/input'],
  3.                          outputs=['concat', 'concat_1'],
  4.                          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/) Powered by Discuz! X3.3