Keras + Tensorflow優化檔位

Question

我安裝了Theano（TH），Tensorflow（TF）和Keras。 基本測試似乎表明，它們與GPU（GTX 1070），Cuda 8.0，cuDNN5.1一起使用。

如果我用TH作爲後端運行cifar10_cnn.py Keras example，它似乎可以正常工作，時間約爲18s/epoch。 如果我用TF運行它然後幾乎（它偶爾有效，不能再現它），優化在每時代以後失去acc = 0.1。這就好像權重沒有更新一樣。

這是一個恥辱，因爲TF後端花費的時間大約是10s/epoch（即使是非常少的幾次）。我使用的是Conda，我對Python很陌生。如果有幫助，「conda list」似乎爲某些軟件包顯示了兩個版本。

如果您有任何線索，請告訴我。謝謝。下面的截圖：

python cifar10_cnn.py 

Using TensorFlow backend. 

I tensorflow/stream_executor/dso_loader.cc:128] successfully opened CUDA library libcublas.so locally 

I tensorflow/stream_executor/dso_loader.cc:128] successfully opened CUDA library libcudnn.so locally 

I tensorflow/stream_executor/dso_loader.cc:128] successfully opened CUDA library libcufft.so locally 

I tensorflow/stream_executor/dso_loader.cc:128] successfully opened CUDA library libcuda.so.1 locally 

I tensorflow/stream_executor/dso_loader.cc:128] successfully opened CUDA library libcurand.so locally 

X_train shape: (50000, 32, 32, 3) 

50000 train samples 

10000 test samples 

Using real-time data augmentation. 

Epoch 1/200 

I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:936] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 

I tensorflow/core/common_runtime/gpu/gpu_device.cc:885] Found device 0 with properties: 

name: GeForce GTX 1070 

major: 6 minor: 1 memoryClockRate (GHz) 1.7845 

pciBusID 0000:01:00.0 

Total memory: 7.92GiB 

Free memory: 7.60GiB 

I tensorflow/core/common_runtime/gpu/gpu_device.cc:906] DMA: 0 

I tensorflow/core/common_runtime/gpu/gpu_device.cc:916] 0: Y 

I tensorflow/core/common_runtime/gpu/gpu_device.cc:975] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GeForce GTX 1070, pci bus id: 0000:01:00.0) 

50000/50000 [==============================] - 11s - loss: 2.3029 - acc: 0.0999 - val_loss: 2.3026 - val_acc: 0.1000 

Epoch 2/200 

50000/50000 [==============================] - 10s - loss: 2.3028 - acc: 0.0980 - val_loss: 2.3026 - val_acc: 0.1000 

Epoch 3/200 

50000/50000 [==============================] - 10s - loss: 2.3028 - acc: 0.0992 - val_loss: 2.3026 - val_acc: 0.1000 

Epoch 4/200 

50000/50000 [==============================] - 10s - loss: 2.3028 - acc: 0.0980 - val_loss: 2.3026 - val_acc: 0.1000 

Epoch 5/200 

13184/50000 [======>.......................] - ETA: 7s - loss: 2.3026 - acc: 0.1044^CTraceback (most recent call last): 

Answer 1

它看起來對我來說，這只是隨機猜測，因爲有10點的可能性，這是時權10％。我唯一能想到的是你的學習速度有點太高。我已經看到高學習率的模型有時會收斂，有時不會收斂。現在在後端，我認爲theano會執行更多優化，所以這可能會略微影響某些內容。嘗試降低學習率10倍，看看它是否收斂。