All predictions returning same value after update to tensorflow-gpu - tensorflow

Question

everything was going well with these cnn to classify MarkovTransitionField sequences, when I was using tensorflow, but then I changed to tensorflow-gpu and all predictions return same value, so model isn't learning (but is fast)
#model 1
def model_1_signal():
model = Sequential()
model.add(Conv2D(73, (5,5), strides = (2,2), activation = 'relu',
padding = 'same', input_shape = (145,5,5),
kernel_initializer = 'he_normal',
bias_initializer = 'zeros'))
model.add(Conv2D(73, (5,5), strides = (2,2), activation = 'relu',
padding = 'same', kernel_initializer = 'he_normal',
bias_initializer = 'zeros'))
model.add(Flatten())
model.add(Dense(2, activation = 'sigmoid',
kernel_initializer = 'glorot_uniform',
bias_initializer = 'zeros'))
model.compile(loss = 'categorical_crossentropy',
optimizer = 'adam',
metrics = ['accuracy'])
return model
def model_2_signal():
model = Sequential()
model.add(Conv2D(73, (5,5), activation = 'relu',
padding = 'same', input_shape = (145,5,5)))
model.add(Dropout(0.2))
model.add(Conv2D(73, (5,5), strides = (2,2), activation = 'relu',
padding = 'same'))
model.add(Dropout(0.2))
model.add(Conv2D(73, (5,5), strides = (2,2), activation = 'relu',
padding = 'same'))
model.add(Dropout(0.2))
model.add(Conv2D(73, (5,5), strides = (2,2), activation = 'relu',
padding = 'same'))
model.add(MaxPooling2D(pool_size = (1,1),strides = 3))
model.add(Dropout(0.2))
model.add(Flatten())
model.add(Dense(64, activation = 'relu'))
model.add(Dropout(0.2))
model.add(Dense(64, activation = 'relu'))
model.add(Dropout(0.2))
model.add(Dense(2, activation = 'sigmoid'))
model.compile(loss = 'categorical_crossentropy',
optimizer = 'adam',
metrics = ['accuracy'])
return model
EPOCHS = 300
BATCH_SIZE = 15
train_X, val_X, train_y, val_y, train_date, val_date = train_test_split(bullish_episodes_img,y,date,test_size = 0.13, shuffle = False)
val_X, test_X, val_y, test_y, val_date, test_date = train_test_split(val_X, val_y, val_date, test_size = 0.38, shuffle = False)
model_1 = model_1_signal()
model_1.fit(train_X,train_y, validation_data=(val_X,val_y),
epochs = EPOCHS, batch_size = BATCH_SIZE, verbose = 2,
shuffle = True)
yhat_model1 = model_1.predict(test_X)
yhat_model1 = np.where(yhat_model1 >= 0.5, 1, 0)
df1 = pd.DataFrame({'signal':yhat_model1[:,1],'test':test_y[:,1],'time':test_date})
df1 = df1.sort_values(by='time')
#model_1.save('/home/f320x/Documents/AT/Py (1)/final_project/new_standard/spyder/spyder/EURCAD/signal_model/signal_model1')
model_2 = model_2_signal()
model_2.fit(train_X,train_y, validation_data=(val_X,val_y),
epochs = EPOCHS, batch_size = BATCH_SIZE, verbose = 2,
shuffle = True)
yhat_model2 = model_2.predict(test_X)
yhat_model2 = np.where(yhat_model2 >= 0.5, 1, 0)
df2 = pd.DataFrame({'signal':yhat_model2[:,1],'test':test_y[:,1],'time':test_date})
df2 = df2.sort_values(by='time')
before transform data to MarkovTransitionField, i scaled all values between 0 and 1 and there's no nan in dataset.
does somebody has a hint?