Some problems about running test part

[TowerTowerLee]

Hello, I used 2080ti, tensorflow-gpu 1.12.0, CUDA 9.0, cudnn7.6.5 to reproduce the code test part, but I encountered a bug in the middle. I found that the reason was that running on 2080ti would crash, so I used CPU to reproduce, Step 1 of test part can run correctly, but there is a problem when running step 2。

WARNING:tensorflow:From /root/anaconda3/envs/python3.6/lib/python3.6/site-packages/tflearn/initializations.py:119: UniformUnitScaling.__init__ (from tensorflow.python.ops.init_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.initializers.variance_scaling instead with distribution=uniform to get equivalent behavior.
Traceback (most recent call last):
  File "/root/anaconda3/envs/python3.6/lib/python3.6/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: Shape must be rank 3 but is rank 4 for 'graph_localproj_1_layer_1/Pad' (op: 'Pad') with input shapes: [3,224,224,16], [3,2].

Would this problem only appear in the CPU version and not in the GPU version? Do you have a good solution?

[TowerTowerLee]

Hi！The above problem has been solved because I added inappropriate padding in the projection part, but I found that similar problems appeared after running for some time.

Iteration 1/8750, Data id 02828884_c069553c08631597cb2a965e75be701c_00.dat
Iteration 2/8750, Data id 04379243_dc5a136f23bd3f31c710d14956729baa_00.dat
2020-06-17 13:29:07.195224: W tensorflow/core/framework/op_kernel.cc:1273] OP_REQUIRES failed at gather_nd_op.cc:50 : Invalid argument: indices[230] = [2, 112, 43] does not index into param shape [3,112,112,32]
2020-06-17 13:29:07.210668: W tensorflow/core/framework/op_kernel.cc:1273] OP_REQUIRES failed at gather_nd_op.cc:50 : Invalid argument: indices[230] = [2, 112, 44] does not index into param shape [3,112,112,32]
2020-06-17 13:29:07.284014: W tensorflow/core/framework/op_kernel.cc:1273] OP_REQUIRES failed at gather_nd_op.cc:50 : Invalid argument: indices[248] = [2, 56, 23] does not index into param shape [3,56,56,64]
2020-06-17 13:29:07.291896: W tensorflow/core/framework/op_kernel.cc:1273] OP_REQUIRES failed at gather_nd_op.cc:50 : Invalid argument: indices[248] = [2, 56, 22] does not index into param shape [3,56,56,64]

Is this caused by the CPU running? Do you encounter similar situations when GPU is running? Hope for your reply！

[lkf1996]

hello! Have you run the train.py successfully？ I got a problem "InvalidArgumenrError : indices[0,7]= -1 is nor in [0,157] " when run in "sess.run(model , feed_dict = feed_dict" .
Hope for your reply ? can we have a communication？

[walsvid]

@lkf1996 I have replied your issue in #11 .