Visualization of Keras models, layer visualization and kernel visualization

Visualization of Keras Models:

Model

Model = sequential () # INPUT:100X100 images with 3 channels, (3) tensors.
# This applies, convolution filters of size 3x3 each. Model.add (Zeropadding2d (1), Input_shape= (3, 3)) Model.add (conv2d (+)' Relu ', padding=' Same ') # Model.add (conv2d (3, 3), activation= ' Relu ', padding= ' same ')) Model.add (Batchnormalization ()) Model.add ( Maxpooling2d (Pool_size= (2, 2)) Model.add (Dropout (0.25)) Model.add (conv2d (3, 3), activation=' Relu ', padding=' Same ',)) # Model.add (conv2d (3, 3), activation= ' Relu ', padding= ' same ',)) Model.add (Batchnormalization ()) Model.add ( Maxpooling2d (Pool_size= (2, 2)) Model.add (Dropout (0.25)) Model.add (conv2d (+ 3, 3), activation=' Relu ', padding=' Same ',)) # Model.add (conv2d (3, 3), activation= ' Relu ', padding= ' same ',)) Model.add (Batchnormalization ()) Model.add ( Maxpooling2d (Pool_size= (2, 2)) Model.add (Dropout (0.25)) Model.add (Averagepooling2d ((5,5))) Model.add (Flatten ()) # Model.add (Dense (activation= ' Relu ')) # Model.add (Dropout (0.5)) Model.add (Dense (label_size, activation=' Softmax '))

1. Layer Visualization:

test_x = [] img_src = Cv2.imdecode (Np.fromfile (R ' c:\temp.tif ', dtype=np.uint8), Cv2. Imread_grayscale) img = cv2.resize (IMG_SRC, (up to), Interpolation=cv2. INTER_CUBIC) # img = Np.random.randint (0,255, (38,38)) img = (255-img)/255 img = Np.reshape (IMG, 1)) Test_x.ap Pend (img) ################################################################### layer = model.layers[1] Weight =  Layer.get_weights () # Print (weight) print (Np.asarray (weight). Shape) MODEL_V1 = Sequential () # input:100x100 images with 3
Channels, (3), tensors.
# This applies, convolution filters of size 3x3 each. Model_v1.add (Zeropadding2d (1, 1), input_shape= (1)) Model_v1.add (conv2d (+ 3, 3), activation=' Relu ', padding=' Same ') # Model.add (conv2d (3, 3), activation= ' Relu ', padding= ' same ')) model_v1.layers[1].set_weights (weight) re = Model_ V1.predict (Np.array (test_x)) print (Np.shape (re)) re = Np.transpose (Re, (0,3,1,2)) forIinchRange (+): Plt.subplot (4,8,i+1) plt.imshow (Re[0][i]) #, cmap= ' Gray ' plt.show () ################################## ################################ MODEL_V2 = sequential () # INPUT:100X100 images with 3 channels (3) Tenso
Rs.
# This applies, convolution filters of size 3x3 each. Model_v2.add (Zeropadding2d (1, 1), input_shape= (1)) Model_v2.add (conv2d (+ 3, 3), activation=' Relu ', padding=' Same ') # Model.add (conv2d (3, 3), activation= ' Relu ', padding= ' same ')) Model_v2.add (Batchnormalization ()) Model_v2.add ( Maxpooling2d (Pool_size= (2, 2)) Model_v2.add (Dropout (0.25)) Model_v2.add (conv2d (3, 3), activation=' Relu ', padding=' Same ',)) print (Len (model_v2.layers)) Layer1 = model.layers[1] weight1 = layer1.get_weights () model_v2.layers[1].set_weights (weight1) Layer5 = model.layers[5] Weight5 = Layer5.get_weights () model_v2.layers[5].set_weights (weight5) Re2 = Model_v2 . Predict (Np.array (test_x)) Re2 = Np.transpose (Re2, (0,3,1,2)) forIinchRange: Plt.subplot (8,8,i+1) plt.imshow (Re2[0][i]) #, cmap= ' Gray ' plt.show () ################################# ################################# model_v3 = sequential () # INPUT:100X100 images with 3 channels (3) Tens
Ors.
# This applies, convolution filters of size 3x3 each. Model_v3.add (Zeropadding2d (1, 1), input_shape= (1)) Model_v3.add (conv2d (+ 3, 3), activation=' Relu ', padding=' Same ') # Model.add (conv2d (3, 3), activation= ' Relu ', padding= ' same ')) Model_v3.add (Batchnormalization ()) Model_v3.add ( Maxpooling2d (Pool_size= (2, 2)) Model_v3.add (Dropout (0.25)) Model_v3.add (conv2d (3, 3), activation=' Relu ', padding=' Same ',)) # Model.add (conv2d (3, 3), activation= ' Relu ', padding= ' same ',)) Model_v3.add (Batchnormalization ()) Model_ V3.add (Maxpooling2d (pool_size= (2, 2)) Model_v3.add (Dropout (0.25)) Model_v3.add (conv2d (+ 3, 3), activation=' Relu ', padding=' Same ',)) print (Len (model_v3.layers)) Layer1 = model.layers[1] weight1 = layer1.get_weights () model_v3.layers[1].set_weights (weight1) Layer5 = model.layers[5] Weight5 = Layer5.get_weights () model_v3.layers[5].set_weights (WEIGHT5) Layer9 = model . layers[9] Weight9 = Layer9.get_weights () model_v3.layers[9].set_weights (weight9) Re3 = Model_v3.predict (Np.array ( test_x)) Re3 = Np.transpose (Re3, (0,3,1,2)) forIinchRange (121): Plt.subplot (11,11,i+1) plt.imshow (Re3[0][i]) #, cmap= ' Gray ' plt.show ()

2.kernel Visualization:

defProcess (x): res = np.clip (x, 0, 1)returnResdefDprocessed (x): res = np.zeros_like (x) Res + = 1 Res[x < 0] = 0 res[x > 1] = 0returnResdefDeprocess_image (x): X-= X.mean () x/= (X.STD () + 1e-5) x *= 0.1 x + = 0.5 x = np.clip (x, 0, 1) x * = 255 x = np.clip (x, 0, 255). Astype (' Uint8 ')returnX forI_kernalinchRange: Input_img=model.input loss = K.mean (model.layers[5].output[:,:,:, I_kernal]) # loss = K.mean (model. output[:, i_kernal]) # Compute the gradient of the input picture wrt this loss grads = K.gradients (loss, input_img  ) [0] # Normalization Trick:we normalize the gradient grads/= (k.sqrt (K.mean (k.square)) + 1e-5) # this function returns the loss and grads given the input picture iterate = K.function ([Input_img, K.learning_phase ()], [Lo SS, grads]) # We start from a gray image with some noise np.random.seed (0) Num_channels=1 img_height=img_w
    idth=38 Input_img_data = (255-np.random.randint (0,255, (1, Img_height, Img_width, num_channels))/255. Failed =False # Run Gradient ascent print ('####################################', i_kernal+1) loss_value_pre=0 forIinchRange (10000): # processed = Process (input_img_data) # predictions = Model.predict (input_img_data) Loss_value, Grads_value = Iterate ([input_img_data,1]) # Grads_value *= dprocessed (input_img_data[0])ifi%1000 = = 0: # print (' predictions: ', np.shape (predictions), Np.argmax (predictions)) print (' Iteration%d/%d, loss:%f '% (I, 10000, loss_value)) print (' Mean Grad:%f '% Np.mean (grads_value))ifAll (Np.abs (Grads_val) < 0.000001 forGrads_valinchGrads_value.flatten ()): failed =True Print' Failed ') Break # print (' image:\n%s '% str (input_img_data[0,0,:,:]))ifLoss_value_pre! = 0 andLoss_value_pre > Loss_value: BreakifLoss_value_pre = = 0:loss_value_pre = loss_value # if Loss_value > 0.99: # Break Input_img_data + = Grads_value * 1 #e-3 Plt.subplot (8, 8, i_kernal+1) # plt.imshow (Process (input_i mg_data[0,:,:,0]) *255). Astype (' uint8 '), cmap= ' greys ') #cmap = ' Greys ' img_re = Deprocess_image (input_img_data[0]) im G_re = Np.reshape (Img_re, (38,38)) plt.imshow (Img_re, cmap=' Greys ') #cmap = ' Greys ' # plt.show () plt.show ()

MODEL.LAYERS[1]

MODEL.LAYERS[5]

MODEL.LAYERS[-1]