Mytest

C\AppData\Local\JetBrains\PyCharm Community Edition 2020.3\plugins\python-ce\helpers\pydev\pydevconsole.py" --mode=client --port=59828

import sys; print('Python %s on %s' % (sys.version, sys.platform))
sys.path.extend(['a/PycharmProjects/cvnn'])

Python 3.8.5 (default, Sep  3 2020, 21:29:08) [MSC v.1916 64 bit (AMD64)]
Type 'copyright', 'credits' or 'license' for more information
IPython 7.19.0 -- An enhanced Interactive Python. Type '?' for help.
PyDev console: using IPython 7.19.0

Python 3.8.5 (default, Sep  3 2020, 21:29:08) [MSC v.1916 64 bit (AMD64)] on win32
In[2]: runPycharmProjects/cvnn/examples/Mytest.py', wdir=/PycharmProjects/cvnn/examples')
2021-02-16 10:49:39.476272: W tensorflow/stream_executor/platform/default/dso_loader.cc:59] Could not load dynamic library 'cudart64_101.dll'; dlerror: cudart64_101.dll not found
2021-02-16 10:49:39.476904: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
2021-02-16 10:49:47.668125: W tensorflow/stream_executor/platform/default/dso_loader.cc:59] Could not load dynamic library 'nvcuda.dll'; dlerror: nvcuda.dll not found
2021-02-16 10:49:47.668705: W tensorflow/stream_executor/cuda/cuda_driver.cc:312] failed call to cuInit: UNKNOWN ERROR (303)
2021-02-16 10:49:47.675070: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:169] retrieving CUDA diagnostic information for host: ip2979
2021-02-16 10:49:47.675722: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:176] hostname: ip2979
2021-02-16 10:49:47.676457: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)to use the following CPU instructions in performance-critical operations:  AVX2
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2021-02-16 10:49:47.687932: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x1f880d390c0 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2021-02-16 10:49:47.688594: I tensorflow/compiler/xla/service/service.cc:176]   StreamExecutor device (0): Host, Default Version
Model: "sequential"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
complex_conv2d (ComplexConv2 (None, 30, 30, 32)        1792      
_________________________________________________________________
complex_avg_pooling2d (Compl (None, 15, 15, 32)        0         
_________________________________________________________________
complex_conv2d_1 (ComplexCon (None, 13, 13, 64)        36992     
_________________________________________________________________
complex_max_pooling2d (Compl (None, 6, 6, 64)          0         
_________________________________________________________________
complex_conv2d_2 (ComplexCon (None, 4, 4, 64)          73856     
_________________________________________________________________
complex_flatten (ComplexFlat (None, 1024)              0         
_________________________________________________________________
complex_dense (ComplexDense) (None, 64)                131200    
_________________________________________________________________
complex_dense_1 (ComplexDens (None, 10)                1300      
=================================================================
Total params: 245,140
Trainable params: 245,140
Non-trainable params: 0
_________________________________________________________________
Epoch 1/50
1563/1563 [==============================] - 133s 85ms/step - loss: 1.5060 - accuracy: 0.4507 - val_loss: 1.3063 - val_accuracy: 0.5288
Epoch 2/50
1563/1563 [==============================] - 140s 90ms/step - loss: 1.1287 - accuracy: 0.5992 - val_loss: 1.0865 - val_accuracy: 0.6195
Epoch 3/50
1563/1563 [==============================] - 138s 88ms/step - loss: 0.9450 - accuracy: 0.6686 - val_loss: 0.9367 - val_accuracy: 0.6764
Epoch 4/50
1563/1563 [==============================] - 137s 88ms/step - loss: 0.8210 - accuracy: 0.7137 - val_loss: 0.9554 - val_accuracy: 0.6745
Epoch 5/50
1563/1563 [==============================] - 135s 87ms/step - loss: 0.7203 - accuracy: 0.7475 - val_loss: 0.8982 - val_accuracy: 0.6969
Epoch 6/50
1563/1563 [==============================] - 133s 85ms/step - loss: 0.6328 - accuracy: 0.7787 - val_loss: 0.8671 - val_accuracy: 0.7053
Epoch 7/50
1563/1563 [==============================] - 139s 89ms/step - loss: 0.5508 - accuracy: 0.8072 - val_loss: 0.8965 - val_accuracy: 0.7076
Epoch 8/50
1563/1563 [==============================] - 137s 88ms/step - loss: 0.4781 - accuracy: 0.8323 - val_loss: 0.9527 - val_accuracy: 0.6985
Epoch 9/50
1563/1563 [==============================] - 136s 87ms/step - loss: 0.4123 - accuracy: 0.8535 - val_loss: 0.9763 - val_accuracy: 0.7117
Epoch 10/50
1563/1563 [==============================] - 136s 87ms/step - loss: 0.3570 - accuracy: 0.8722 - val_loss: 1.0548 - val_accuracy: 0.7046
Epoch 11/50
1563/1563 [==============================] - 136s 87ms/step - loss: 0.3046 - accuracy: 0.8911 - val_loss: 1.1623 - val_accuracy: 0.7041
Epoch 12/50
1563/1563 [==============================] - 136s 87ms/step - loss: 0.2598 - accuracy: 0.9067 - val_loss: 1.2645 - val_accuracy: 0.6987
Epoch 13/50
1563/1563 [==============================] - 138s 88ms/step - loss: 0.2284 - accuracy: 0.9190 - val_loss: 1.3244 - val_accuracy: 0.7043
Epoch 14/50
1563/1563 [==============================] - 139s 89ms/step - loss: 0.2087 - accuracy: 0.9256 - val_loss: 1.4699 - val_accuracy: 0.6830
Epoch 15/50
1563/1563 [==============================] - 136s 87ms/step - loss: 0.1854 - accuracy: 0.9344 - val_loss: 1.5103 - val_accuracy: 0.6938
Epoch 16/50
1563/1563 [==============================] - 137s 87ms/step - loss: 0.1684 - accuracy: 0.9400 - val_loss: 1.5969 - val_accuracy: 0.6968
Epoch 17/50
1563/1563 [==============================] - 138s 88ms/step - loss: 0.1532 - accuracy: 0.9455 - val_loss: 1.6835 - val_accuracy: 0.6971
Epoch 18/50
1563/1563 [==============================] - 133s 85ms/step - loss: 0.1455 - accuracy: 0.9492 - val_loss: 1.7654 - val_accuracy: 0.6950
Epoch 19/50
1563/1563 [==============================] - 131s 84ms/step - loss: 0.1311 - accuracy: 0.9550 - val_loss: 1.9224 - val_accuracy: 0.6953
Epoch 20/50
1563/1563 [==============================] - 131s 84ms/step - loss: 0.1335 - accuracy: 0.9532 - val_loss: 1.8647 - val_accuracy: 0.6922
Epoch 21/50
1563/1563 [==============================] - 130s 83ms/step - loss: 0.1256 - accuracy: 0.9562 - val_loss: 1.9918 - val_accuracy: 0.6887
Epoch 22/50
1563/1563 [==============================] - 130s 83ms/step - loss: 0.1224 - accuracy: 0.9574 - val_loss: 2.0633 - val_accuracy: 0.6889
Epoch 23/50
1563/1563 [==============================] - 130s 83ms/step - loss: 0.1213 - accuracy: 0.9598 - val_loss: 2.2803 - val_accuracy: 0.6873
Epoch 24/50
1563/1563 [==============================] - 130s 83ms/step - loss: 0.1150 - accuracy: 0.9610 - val_loss: 2.2305 - val_accuracy: 0.6857
Epoch 25/50
1563/1563 [==============================] - 131s 84ms/step - loss: 0.1100 - accuracy: 0.9628 - val_loss: 2.1134 - val_accuracy: 0.6895
Epoch 26/50
1563/1563 [==============================] - 131s 84ms/step - loss: 0.1072 - accuracy: 0.9640 - val_loss: 2.4607 - val_accuracy: 0.6932
Epoch 27/50
1563/1563 [==============================] - 131s 84ms/step - loss: 0.1071 - accuracy: 0.9646 - val_loss: 2.4123 - val_accuracy: 0.6797
Epoch 28/50
1563/1563 [==============================] - 131s 84ms/step - loss: 0.1044 - accuracy: 0.9645 - val_loss: 2.3938 - val_accuracy: 0.6885
Epoch 29/50
1563/1563 [==============================] - 131s 84ms/step - loss: 0.1008 - accuracy: 0.9663 - val_loss: 2.3439 - val_accuracy: 0.6867
Epoch 30/50
1563/1563 [==============================] - 131s 84ms/step - loss: 0.1015 - accuracy: 0.9666 - val_loss: 2.4318 - val_accuracy: 0.6932
Epoch 31/50
1563/1563 [==============================] - 131s 83ms/step - loss: 0.0934 - accuracy: 0.9699 - val_loss: 2.4682 - val_accuracy: 0.6940
Epoch 32/50
1563/1563 [==============================] - 131s 84ms/step - loss: 0.1023 - accuracy: 0.9679 - val_loss: 2.5649 - val_accuracy: 0.6870
Epoch 33/50
1563/1563 [==============================] - 130s 83ms/step - loss: 0.0902 - accuracy: 0.9705 - val_loss: 2.6804 - val_accuracy: 0.6796
Epoch 34/50
1563/1563 [==============================] - 130s 83ms/step - loss: 0.0931 - accuracy: 0.9703 - val_loss: 2.6035 - val_accuracy: 0.6746
Epoch 35/50
1563/1563 [==============================] - 129s 83ms/step - loss: 0.0884 - accuracy: 0.9706 - val_loss: 2.7067 - val_accuracy: 0.6906
Epoch 36/50
1563/1563 [==============================] - 129s 83ms/step - loss: 0.0904 - accuracy: 0.9707 - val_loss: 2.7004 - val_accuracy: 0.6898
Epoch 37/50
1563/1563 [==============================] - 132s 84ms/step - loss: 0.0926 - accuracy: 0.9718 - val_loss: 2.6711 - val_accuracy: 0.6877
Epoch 38/50
1563/1563 [==============================] - 129s 82ms/step - loss: 0.0912 - accuracy: 0.9718 - val_loss: 2.6544 - val_accuracy: 0.6853
Epoch 39/50
1563/1563 [==============================] - 130s 83ms/step - loss: 0.0840 - accuracy: 0.9742 - val_loss: 2.6343 - val_accuracy: 0.6867
Epoch 40/50
1563/1563 [==============================] - 131s 84ms/step - loss: 0.0885 - accuracy: 0.9718 - val_loss: 2.7846 - val_accuracy: 0.6895
Epoch 41/50
1563/1563 [==============================] - 130s 83ms/step - loss: 0.0927 - accuracy: 0.9723 - val_loss: 2.8534 - val_accuracy: 0.6864
Epoch 42/50
1563/1563 [==============================] - 129s 82ms/step - loss: 0.0812 - accuracy: 0.9752 - val_loss: 2.8807 - val_accuracy: 0.6858
Epoch 43/50
1563/1563 [==============================] - 130s 83ms/step - loss: 0.0852 - accuracy: 0.9729 - val_loss: 2.8798 - val_accuracy: 0.6887
Epoch 44/50
1563/1563 [==============================] - 129s 83ms/step - loss: 0.0819 - accuracy: 0.9750 - val_loss: 2.8497 - val_accuracy: 0.6857
Epoch 45/50
1563/1563 [==============================] - 129s 82ms/step - loss: 0.0854 - accuracy: 0.9734 - val_loss: 2.8855 - val_accuracy: 0.6894
Epoch 46/50
1563/1563 [==============================] - 129s 83ms/step - loss: 0.0785 - accuracy: 0.9757 - val_loss: 3.2925 - val_accuracy: 0.6747
Epoch 47/50
1563/1563 [==============================] - 129s 83ms/step - loss: 0.0746 - accuracy: 0.9773 - val_loss: 3.0221 - val_accuracy: 0.6919
Epoch 48/50
1563/1563 [==============================] - 130s 83ms/step - loss: 0.0810 - accuracy: 0.9751 - val_loss: 3.1343 - val_accuracy: 0.6896
Epoch 49/50
1563/1563 [==============================] - 129s 83ms/step - loss: 0.0873 - accuracy: 0.9746 - val_loss: 3.2250 - val_accuracy: 0.6886
Epoch 50/50
1563/1563 [==============================] - 129s 83ms/step - loss: 0.0778 - accuracy: 0.9770 - val_loss: 3.0985 - val_accuracy: 0.6886