There is something wrong when i run the program。

[sdds-torch]

Hello,thank you very much for sharing the program.But when i run the attack.py on IncRes_V2 and Inc_v3,there is something wrong with the program.With the IncRes_V2,there is an error:ValueError: 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].And with the Inc_v3,there is an error:Tensor name "InceptionV3/AuxLogits/Conv2d_2a_3x3/BatchNorm/beta" not found in checkpoint files ./models_tf/inception_v3.ckpt [[node save/RestoreV2 (defined at attack.py:267) ]] Can you tell me what's wrong? Thank you very much!

[hcguoO0]

Do you use InceptionResnetV2/AuxLogits/Conv2d_2a_5x5/Conv2D and InceptionV3/AuxLogits/Conv2d_2a_3x3/BatchNorm/beta as the layer_name parameter?

[sdds-torch]

I used InceptionResnetV2/InceptionResnetV2/Conv2d_4a_3x3/Relu for IncRes_v2 and InceptionV3/InceptionV3/Mixed_5b/concat for Inc-v3 ,but i just used the InceptionResnetV2/AuxLogits/Conv2d_2a_5x5/Conv2D and InceptionV3/AuxLogits/Conv2d_2a_3x3/BatchNorm/beta as the layer_name parameter,it still some errors,for Inc-v3:Traceback (most recent call last): File "/home/tensor/.conda/envs/tensorflow1.9/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1864, in _create_c_op c_op = c_api.TF_FinishOperation(op_desc) tensorflow.python.framework.errors_impl.InvalidArgumentError: Dimensions must be equal, but are 748 and 20 for 'mul_1' (op: 'Mul') with input shapes: [748], [20].

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "attack.py", line 329, in tf.app.run() File "/home/tensor/.conda/envs/tensorflow1.9/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 40, in run _run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef) File "/home/tensor/.conda/envs/tensorflow1.9/lib/python3.6/site-packages/absl/app.py", line 303, in run _run_main(main, args) File "/home/tensor/.conda/envs/tensorflow1.9/lib/python3.6/site-packages/absl/app.py", line 251, in _run_main sys.exit(main(argv)) File "attack.py", line 229, in main loss = get_fia_loss(opt_operations,weights_ph) File "attack.py", line 110, in get_fia_loss loss += tf.reduce_sum(adv_tensorweights) / tf.cast(tf.size(layer), tf.float32) File "/home/tensor/.conda/envs/tensorflow1.9/lib/python3.6/site-packages/tensorflow/python/ops/math_ops.py", line 884, in binary_op_wrapper return func(x, y, name=name) File "/home/tensor/.conda/envs/tensorflow1.9/lib/python3.6/site-packages/tensorflow/python/ops/math_ops.py", line 1180, in _mul_dispatch return gen_math_ops.mul(x, y, name=name) File "/home/tensor/.conda/envs/tensorflow1.9/lib/python3.6/site-packages/tensorflow/python/ops/gen_math_ops.py", line 6490, in mul "Mul", x=x, y=y, name=name) File "/home/tensor/.conda/envs/tensorflow1.9/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 788, in _apply_op_helper op_def=op_def) File "/home/tensor/.conda/envs/tensorflow1.9/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 507, in new_func return func(args, **kwargs) File "/home/tensor/.conda/envs/tensorflow1.9/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3616, in create_op op_def=op_def) File "/home/tensor/.conda/envs/tensorflow1.9/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 2027, in init control_input_ops) File "/home/tensor/.conda/envs/tensorflow1.9/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1867, in _create_c_op raise ValueError(str(e)) ValueError: Dimensions must be equal, but are 748 and 20 for 'mul_1' (op: 'Mul') with input shapes: [748], [20].

And for InceptionResnetV2: File "attack.py", line 329, in tf.app.run() File "/home/tensor/.conda/envs/tensorflow1.9/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 40, in run _run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef) File "/home/tensor/.conda/envs/tensorflow1.9/lib/python3.6/site-packages/absl/app.py", line 303, in run _run_main(main, args) File "/home/tensor/.conda/envs/tensorflow1.9/lib/python3.6/site-packages/absl/app.py", line 251, in _run_main sys.exit(main(argv)) File "attack.py", line 211, in main logits, end_points = network_fn(x) File "/data/sdd/biye2/FIA-main/nets/nets_factory.py", line 123, in network_fn return func(images, num_classes, is_training=is_training,reuse=tf.AUTO_REUSE) File "/data/sdd/biye2/FIA-main/nets/inception_resnet_v2.py", line 307, in inception_resnet_v2 padding='VALID', scope='Conv2d_2a_5x5') File "/home/tensor/.conda/envs/tensorflow1.9/lib/python3.6/site-packages/tensorflow/contrib/framework/python/ops/arg_scope.py", line 182, in func_with_args return func(*args, current_args) File "/home/tensor/.conda/envs/tensorflow1.9/lib/python3.6/site-packages/tensorflow/contrib/layers/python/layers/layers.py", line 1159, in convolution2d conv_dims=2) File "/home/tensor/.conda/envs/tensorflow1.9/lib/python3.6/site-packages/tensorflow/contrib/framework/python/ops/arg_scope.py", line 182, in func_with_args return func(*args, *current_args) File "/home/tensor/.conda/envs/tensorflow1.9/lib/python3.6/site-packages/tensorflow/contrib/layers/python/layers/layers.py", line 1057, in convolution outputs = layer.apply(inputs) File "/home/tensor/.conda/envs/tensorflow1.9/lib/python3.6/site-packages/tensorflow/python/keras/engine/base_layer.py", line 1479, in apply return self.call(inputs, args, kwargs) File "/home/tensor/.conda/envs/tensorflow1.9/lib/python3.6/site-packages/tensorflow/python/layers/base.py", line 537, in call outputs = super(Layer, self).call(inputs, *args, *kwargs) File "/home/tensor/.conda/envs/tensorflow1.9/lib/python3.6/site-packages/tensorflow/python/keras/engine/base_layer.py", line 634, in call outputs = call_fn(inputs, args, **kwargs) File "/home/tensor/.conda/envs/tensorflow1.9/lib/python3.6/site-packages/tensorflow/python/autograph/impl/api.py", line 149, in wrapper raise e.ag_error_metadata.to_exception(type(e)) ValueError: in converted code: relative to /home/tensor/.conda/envs/tensorflow1.9/lib/python3.6/site-packages/tensorflow/python:

keras/layers/convolutional.py:196 call
    outputs = self._convolution_op(inputs, self.kernel)
ops/nn_ops.py:1079 __call__
    return self.conv_op(inp, filter)
ops/nn_ops.py:635 __call__
    return self.call(inp, filter)
ops/nn_ops.py:234 __call__
    name=self.name)
ops/nn_ops.py:1953 conv2d
    name=name)
ops/gen_nn_ops.py:1071 conv2d
    data_format=data_format, dilations=dilations, name=name)
framework/op_def_library.py:788 _apply_op_helper
    op_def=op_def)
util/deprecation.py:507 new_func
    return func(*args, **kwargs)
framework/ops.py:3616 create_op
    op_def=op_def)
framework/ops.py:2027 __init__
    control_input_ops)
framework/ops.py:1867 _create_c_op
    raise ValueError(str(e))

ValueError: 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].

[hcguoO0]

So did it occour these errors when you use InceptionResnetV2/InceptionResnetV2/Conv2d_4a_3x3/Relu for IncRes_v2 and InceptionV3/InceptionV3/Mixed_5b/concat for Inc-v3?

[sdds-torch]

yes,it did.

[hcguoO0]

Have you changed the code?

[sdds-torch]

No,I haven't

---Original--- From: "Hengchang @.> Date: 2021/12/11 18:57:52 To: @.>; Cc: @.**@.>; Subject: Re: [hcguoO0/FIA] There is something wrong when i run the program。 (Issue #8)

Have you changed the code?

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android.

[hcguoO0]

I download the code and run python attack.py --model_name inception_v3 --attack_method FIA --layer_name InceptionV3/InceptionV3/Mixed_5b/concat --output_dir ./adv/fia/ --image_size 299 --ens 30 --probb 0.7

and it does not occur any errors

[sdds-torch]

Okay,i tried it again,and it works.Thank you very much!

[cyy280113999]

i just forget the " --image_size 299" when running the "attack.py", then the same error occured. but i found code "utils.image_size[model_name]" in the script "verify.py", it automatically choose the size. so why did "attack.py" still require specific "image_size"?