Q&A
前提・実現したいこと
2つの画像を判別する自作モデルを使用してGuidedGrad-CAMを使用したいがエラー文の解決がわからないです。
発生している問題・エラーメッセージ
IndexError Traceback (most recent call last) <ipython-input-27-d83413f66707> in <module> 121 predictions = model.predict(preprocessed_input) 122 predicted_class = np.argmax(predictions) --> 123 cam, heatmap = grad_cam(model, preprocessed_input, predicted_class, "block5_conv3") 124 cv2.imwrite("gradcam.jpg", cam) 125 <ipython-input-27-d83413f66707> in grad_cam(input_model, image, category_index, layer_name) 90 loss = K.sum(model.layers[-1].output) 91 ---> 92 conv_output = [l for l in model.layers if l.name is layer_name][0].output 93 94 grads = normalize(K.gradients(loss, conv_output)[0]) IndexError: list index out of range
該当のソースコード
from keras.preprocessing import image from keras.layers.core import Lambda from keras.models import Sequential from tensorflow.python.framework import ops import keras.backend as K import tensorflow as tf import numpy as np import keras import sys import cv2 def target_category_loss(x, category_index, nb_classes): return tf.multiply(x, K.one_hot([category_index], nb_classes)) def target_category_loss_output_shape(input_shape): return input_shape def normalize(x): # utility function to normalize a tensor by its L2 norm return x / (K.sqrt(K.mean(K.square(x))) + 1e-5) def load_image(path): img_path = path img = image.load_img(img_path, target_size=(224, 224)) x = image.img_to_array(img) x = np.expand_dims(x, axis=0) x = preprocess_input(x) return x def register_gradient(): if "GuidedBackProp" not in ops._gradient_registry._registry: @ops.RegisterGradient("GuidedBackProp") def _GuidedBackProp(op, grad): dtype = op.inputs[0].dtype return grad * tf.cast(grad > 0., dtype) * \ tf.cast(op.inputs[0] > 0., dtype) def compile_saliency_function(model, activation_layer='conv2'): input_img = my_model.input layer_dict = dict([(layer.name, layer) for layer in model.layers[1:]]) layer_output = layer_dict[activation_layer].output max_output = K.max(layer_output, axis=3) saliency = K.gradients(K.sum(max_output), input_img)[0] return K.function([input_img, K.learning_phase()], [saliency]) def modify_backprop(model, name): g = tf.get_default_graph() with g.gradient_override_map({'Relu': name}): new_model = my_model return new_model def deprocess_image(x): if np.ndim(x) > 3: x = np.squeeze(x) x -= x.mean() x /= (x.std() + 1e-5) x *= 0.1 x += 0.5 x = np.clip(x, 0, 1) x *= 255 if K.image_dim_ordering() == 'tf': x = x.transpose((0, 1, 2)) x = np.clip(x, 0, 255).astype('uint8') return x def grad_cam(input_model, image, category_index, layer_name): nb_classes = 1000 model = Sequential() model.add(input_model) target_layer = lambda x: target_category_loss(x, category_index, nb_classes) x = input_model.layers[-1].output x = Lambda(target_layer, output_shape=target_category_loss_output_shape)(x) model = keras.models.Model(input_model.layers[0].input, x) loss = K.sum(model.layers[-1].output) conv_output = [l for l in model.layers if l.name is layer_name][0].output grads = normalize(K.gradients(loss, conv_output)[0]) gradient_function = K.function([model.layers[0].input], [conv_output, grads]) output, grads_val = gradient_function([image]) output, grads_val = output[0, :], grads_val[0, :, :, :] weights = np.mean(grads_val, axis = (0, 1)) cam = np.zeros(output.shape[0 : 2], dtype = np.float32) for i, w in enumerate(weights): cam += w * output[:, :, i] cam = cv2.resize(cam, (224, 224)) cam = np.maximum(cam, 0) heatmap = (cam - np.min(cam))/(np.max(cam) - np.min(cam)) image = image[0, :] image -= np.min(image) image = np.minimum(image, 255) cam = cv2.applyColorMap(np.uint8(255*heatmap), cv2.COLORMAP_JET) cam = np.float32(cam) + np.float32(image) cam = 255 * cam / np.max(cam) return np.uint8(cam), heatmap preprocessed_input = load_image("./1360.jpg") model = load_model('my_model.h5') predictions = model.predict(preprocessed_input) predicted_class = np.argmax(predictions) cam, heatmap = grad_cam(model, preprocessed_input, predicted_class, "block5_conv3") cv2.imwrite("gradcam.jpg", cam) register_gradient() guided_model = modify_backprop(model, 'GuidedBackProp') saliency_fn = compile_saliency_function(guided_model) saliency = saliency_fn([preprocessed_input, 0]) gradcam = saliency[0] * heatmap[..., np.newaxis] cv2.imwrite("guided_gradcam.jpg", deprocess_image(gradcam))
補足情報（FW/ツールのバージョンなど）
_________________________________________________________________ Layer (type) Output Shape Param # ================================================================= input_1 (InputLayer) (None, 224, 224, 3) 0 _________________________________________________________________ block1_conv1 (Conv2D) (None, 224, 224, 64) 1792 _________________________________________________________________ block1_conv2 (Conv2D) (None, 224, 224, 64) 36928 _________________________________________________________________ block1_pool (MaxPooling2D) (None, 112, 112, 64) 0 _________________________________________________________________ block2_conv1 (Conv2D) (None, 112, 112, 128) 73856 _________________________________________________________________ block2_conv2 (Conv2D) (None, 112, 112, 128) 147584 _________________________________________________________________ block2_pool (MaxPooling2D) (None, 56, 56, 128) 0 _________________________________________________________________ block3_conv1 (Conv2D) (None, 56, 56, 256) 295168 _________________________________________________________________ block3_conv2 (Conv2D) (None, 56, 56, 256) 590080 _________________________________________________________________ block3_conv3 (Conv2D) (None, 56, 56, 256) 590080 _________________________________________________________________ block3_pool (MaxPooling2D) (None, 28, 28, 256) 0 _________________________________________________________________ block4_conv1 (Conv2D) (None, 28, 28, 512) 1180160 _________________________________________________________________ block4_conv2 (Conv2D) (None, 28, 28, 512) 2359808 _________________________________________________________________ block4_conv3 (Conv2D) (None, 28, 28, 512) 2359808 _________________________________________________________________ block4_pool (MaxPooling2D) (None, 14, 14, 512) 0 _________________________________________________________________ block5_conv1 (Conv2D) (None, 14, 14, 512) 2359808 _________________________________________________________________ block5_conv2 (Conv2D) (None, 14, 14, 512) 2359808 _________________________________________________________________ block5_conv3 (Conv2D) (None, 14, 14, 512) 2359808 _________________________________________________________________ block5_pool (MaxPooling2D) (None, 7, 7, 512) 0 _________________________________________________________________ flatten (Flatten) (None, 25088) 0 _________________________________________________________________ fc1 (Dense) (None, 4096) 102764544 _________________________________________________________________ fc2 (Dense) (None, 4096) 16781312 _________________________________________________________________ predictions (Dense) (None, 1000) 4097000 ================================================================= Total params: 138,357,544 Trainable params: 138,357,544 Non-trainable params: 0
回答1件
0
ベストアンサー
Python
1conv_output = [l for l in model.layers if l.name is layer_name][0].output
この行を分割して、原因を特定してください。
おそらく、「 [l for l in model.layers if l.name is layer_name]」これの結果がありません。
投稿2019/10/17 03:04
総合スコア995
あなたの回答
tips
プレビュー
バッドをするには、ログインかつ
こちらの条件を満たす必要があります。