python - tensorflow TypeError: float() argument must be a string or a number, not 'dict' -

i have problem. try execute code got error.

import matplotlib.pyplot plt # visualizations shown in notebook. %matplotlib inline import glob import cv2 import numpy np  def plot_figures(figures, nrows, ncols, labels=none):     fig, axs = plt.subplots(ncols=ncols, nrows=nrows, figsize=(12, 14))     axs = axs.ravel()     index, title in zip(range(len(figures)), figures):         axs[index].imshow(figures[title], plt.gray())         if(labels != none):            axs[index].set_title(labels[index])         else:             axs[index].set_title(title)          axs[index].set_axis_off()      plt.tight_layout()  ### visualize network's feature maps here. ### feel free use many code cells needed.  # image_input: test image being fed network produce feature maps # tf_activation: should tf variable name used during training procedure represents calculated state of specific weight layer # activation_min/max: can used view activation contrast in more detail, default matplot sets min , max actual min , max values of output # plt_num: used plot out multiple different weight feature map sets on same block, extend plt number each new feature map entry  def outputfeaturemap(image_input, tf_activation, activation_min=-1, activation_max=-1 ,plt_num=1):     # here make sure preprocess image_input in way network expects     # size, normalization, ect if needed     # image_input =     # note: x should same name network's tensorflow data placeholder variable     # if error tf_activation not defined maybe having trouble accessing variable inside function     activation = tf_activation.eval(session=sess,feed_dict={x : image_input})     featuremaps = activation.shape[3]     plt.figure(plt_num, figsize=(15,15))     featuremap in range(featuremaps):         plt.subplot(6,8, featuremap+1) # sets number of feature maps show on each row , column         plt.title('featuremap ' + str(featuremap)) # displays feature map number         if activation_min != -1 & activation_max != -1:             plt.imshow(activation[0,:,:, featuremap], interpolation="nearest", vmin =activation_min, vmax=activation_max, cmap="gray")         elif activation_max != -1:             plt.imshow(activation[0,:,:, featuremap], interpolation="nearest", vmax=activation_max, cmap="gray")         elif activation_min !=-1:             plt.imshow(activation[0,:,:, featuremap], interpolation="nearest", vmin=activation_min, cmap="gray")         else:             plt.imshow(activation[0,:,:, featuremap], interpolation="nearest", cmap="gray")         my_images = sorted(glob.glob('./traffic_images/*.jpg')) my_labels = np.array([1, 28, 17, 10, 33]) name_values = np.genfromtxt('signnames.csv', skip_header=1, dtype=[('myint','i8'), ('mysring','s55')], delimiter=',')  figures = {} labels = {} my_signs = [] index = 0 my_image in my_images:     img = cv2.cvtcolor(cv2.imread(my_image), cv2.color_bgr2rgb)     my_signs.append(img)     figures[index] = img     labels[index] = name_values[my_labels[index]][1].decode('ascii')     index += 1  plot_figures(figures, 5, 1, labels)   ### run predictions here , use model output prediction each image. ### make sure pre-process images same pre-processing pipeline used earlier. ### feel free use many code cells needed.  my_signs = np.array(my_signs)  tf.session() sess:     sess.run(tf.global_variables_initializer())     saver.restore(sess, "./lenet")     my_accuracy = evaluate(my_signs, my_labels)     print("my data set accuracy = {:.3f}".format(my_accuracy))      ### calculate accuracy these 5 new images.  ### example, if model predicted 1 out of 5 signs correctly, it's 20% accurate on these new images. my_single_item_array = [] my_single_item_label_array = []  = 0  in range(5):     my_single_item_array.append(my_signs[i])     my_single_item_label_array.append(my_labels[i])      tf.session() sess:         sess.run(tf.global_variables_initializer())         saver.restore(sess, "./lenet")         my_accuracy = evaluate(my_single_item_array, my_single_item_label_array)         print('image {}'.format(i+1))         print("image accuracy = {:.3f}".format(my_accuracy))         print()  k_size = 5 softmax_logits = tf.nn.softmax(logits) top_k = tf.nn.top_k(softmax_logits, k=k_size)  tf.session() sess:     sess.run(tf.global_variables_initializer())     saver.restore(sess, "./lenet")     my_softmax_logits = sess.run(softmax_logits, feed_dict={x: my_signs})     my_top_k = sess.run(top_k, feed_dict={x: my_signs})     in range(5):         figures = {}         labels = {}                figures[0] = my_signs[i]         labels[0] = "original"                j in range(k_size):             labels[j+1] = 'guess {} : ({:.0f}%)'.format(j+1, 100*my_top_k[0][i][j])             figures[j+1] = x_valid[np.argwhere(y_valid == my_top_k[1][i][j])[0]].squeeze()         plot_figures(figures, 1, 6, labels)          ymax = figures[0].max()         ymin = figures[0].min()         outputfeaturemap(image_input=figures, tf_activation=softmax_logits, activation_min=ymin, activation_max=ymax , plt_num=k_size) 

but got error message

    --------------------------------------------------------------------------- typeerror                                 traceback (most recent call last) <ipython-input-22-58bf65741b75> in <module>()     122         ymax = figures[0].max()     123         ymin = figures[0].min() --> 124         outputfeaturemap(image_input=figures, tf_activation=softmax_logits, activation_min=ymin, activation_max=ymax , plt_num=k_size)     125      126   <ipython-input-22-58bf65741b75> in outputfeaturemap(image_input, tf_activation, activation_min, activation_max, plt_num)      38     # note: x should same name network's tensorflow data placeholder variable      39     # if error tf_activation not defined maybe having trouble accessing variable inside function ---> 40     activation = tf_activation.eval(session=sess,feed_dict={x : image_input})      41     featuremaps = activation.shape[3]      42     plt.figure(plt_num, figsize=(15,15))  /home/carnd/anaconda3/envs/carnd-term1/lib/python3.5/site-packages/tensorflow/python/framework/ops.py in eval(self, feed_dict, session)     573      574     """ --> 575     return _eval_using_default_session(self, feed_dict, self.graph, session)     576      577   /home/carnd/anaconda3/envs/carnd-term1/lib/python3.5/site-packages/tensorflow/python/framework/ops.py in _eval_using_default_session(tensors, feed_dict, graph, session)    3631                        "the tensor's graph different session's "    3632                        "graph.") -> 3633   return session.run(tensors, feed_dict)    3634     3635   /home/carnd/anaconda3/envs/carnd-term1/lib/python3.5/site-packages/tensorflow/python/client/session.py in run(self, fetches, feed_dict, options, run_metadata)     764     try:     765       result = self._run(none, fetches, feed_dict, options_ptr, --> 766                          run_metadata_ptr)     767       if run_metadata:     768         proto_data = tf_session.tf_getbuffer(run_metadata_ptr)  /home/carnd/anaconda3/envs/carnd-term1/lib/python3.5/site-packages/tensorflow/python/client/session.py in _run(self, handle, fetches, feed_dict, options, run_metadata)     935                 ' larger type (e.g. int64).')     936  --> 937           np_val = np.asarray(subfeed_val, dtype=subfeed_dtype)     938      939           if not subfeed_t.get_shape().is_compatible_with(np_val.shape):  /home/carnd/anaconda3/envs/carnd-term1/lib/python3.5/site-packages/numpy/core/numeric.py in asarray(a, dtype, order)     480      481     """ --> 482     return array(a, dtype, copy=false, order=order)     483      484 def asanyarray(a, dtype=none, order=none):  typeerror: float() argument must string or number, not 'dict' 

i not sure if problem tf_activation=softmax_logits or if else. have idea???