Losing ResNet50 with Keras 2

Since upgrading to Keras 2, I've been seeing nan lost when trying to tune ResNet50. Loss and precision looks ok if I use one convolutional layer (commented below) instead of resnet. Am I missing something that has changed with Keras 2?

from keras.applications.resnet50 import ResNet50
from keras.layers import Flatten, Dense, Input, Conv2D, Activation, Flatten
from keras.layers.pooling import MaxPooling2D
from keras.models import Model
from keras.optimizers import SGD
import numpy as np

inp = Input(batch_shape=(32, 224, 224, 3), name='input_image')

### resnet
modelres = ResNet50(weights="imagenet", include_top=False, input_tensor=inp)
x = modelres.output
x = Flatten()(x)

### single convolutional layer
#x = Conv2D(32, (3,3))(inp)
#x = Activation('relu')(x)
#x = MaxPooling2D(pool_size=(3,3))(x)
#x = Flatten()(x)
#x = Dense(units=32)(x)
predictions = Dense(units=2, kernel_initializer="he_normal", activation="softmax")(x) 

model = Model(inputs=inp, outputs=predictions)
model.compile(SGD(lr=.001, momentum=0.9), "categorical_crossentropy", metrics=["accuracy"])

# generate images of all ones with the same label
def gen():
    while True:
        x_data = np.ones((32,224,224,3)).astype('float32')
        y_data = np.zeros((32,2)).astype('float32')
        y_data[:,1]=1.0
        yield x_data, y_data

model.fit_generator(gen(), 10, validation_data=gen(), validation_steps=1)

      

        
        
        
      

    

The beginning and end model.summary()

looks like this:

____________________________________________________________________________________________________
Layer (type)                     Output Shape          Param #     Connected to
====================================================================================================
input_image (InputLayer)         (32, 224, 224, 3)     0
____________________________________________________________________________________________________
zero_padding2d_1 (ZeroPadding2D) (32, 230, 230, 3)     0
____________________________________________________________________________________________________
conv1 (Conv2D)                   (32, 112, 112, 64)    9472

...

avg_pool (AveragePooling2D)      (32, 1, 1, 2048)      0
____________________________________________________________________________________________________
flatten_1 (Flatten)              (32, 2048)            0
____________________________________________________________________________________________________
dense_1 (Dense)                  (32, 2)               4098
====================================================================================================

      

        
        
        
      

    

Exit for training:

Epoch 1/1
10/10 [==============================] - 30s - loss: nan - acc: 0.0000e+00 - val_loss: nan - val_acc: 0.0000e+00