hcguoO0/FIA

使用其他模型中间层参数会报错

Opened this issue · 2 comments

Mercy0216 commented

使用Inceptionv3模型的中间层参数: InceptionV3/InceptionV3/Mixed_5b/concat
运行会报错
tensorflow.python.framework.errors_impl.NotFoundError: Tensor name "InceptionV3/AuxLogits/Conv2d_2a_3x3/BatchNorm/beta" not found in checkpoint files ./models_tf/inception_v3.ckpt
[[{{node save/RestoreV2}} = RestoreV2[dtypes=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, ..., DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2/tensor_names, save/RestoreV2/shape_and_slices)]]
1695695180588

Mo01iHt commented
Mercy0216 commented

使用InceptionResnetV2模型的中间层参数: InceptionResnetV2/InceptionResnetV2/Conv2d_4a_3x3/Relu
运行会报错
Traceback (most recent call last):
File "E:\Anaconda3\envs\DA\lib\site-packages\tensorflow\python\framework\ops.py", line 1628, in _create_c_op
c_op = c_api.TF_FinishOperation(op_desc)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Negative dimension size caused by subtracting 5 from 3 for 'InceptionResnetV2/AuxLogits/Conv2d_2a_5x5/Conv2D' (op: 'Conv2D') with input shapes: [40,3,3,128], [5,5,128,768].
1695695682793