編集履歴

質問編集履歴

コードが見にくかったため

2021/05/10 12:46

投稿

shujiu

スコア3

test CHANGED Viewed

File without changes

test CHANGED Viewed

File without changes

コードが見にくかったため

2021/05/10 12:46

投稿

shujiu

スコア3

test CHANGED Viewed

File without changes

test CHANGED Viewed

@@ -18,8 +18,6 @@
 ```
-### 該当のソースコード
 ```python
 import torch
@@ -158,8 +156,6 @@
 model.class_to_idx = all_data.class_to_idx
 model.idx_to_class = {
@@ -192,6 +188,8 @@
+    #Initializing some variables
     valid_loss_min = np.Inf
     stop_count = 0
@@ -242,7 +240,7 @@
+            # Track train loss by multiplying average loss by number of examples in batch
             train_loss += loss.item() * data.size(0)
@@ -334,50 +332,220 @@
             stop_count += 1
-            if stop_count >= early_stop:
-                print(f'\nEarly Stopping Total epochs: {epoch}. Best epoch: {best_epoch} with loss: {valid_loss_min:.2f} and acc: {100 * valid_acc:.2f}%')
-                model.load_state_dict(torch.load(save_location))
-                model.optimizer = optimizer
-                history = pd.DataFrame(history, columns=['train_loss', 'valid_loss', 'train_acc','valid_acc'])
-                return model, history
-    model.optimizer = optimizer
-    print(f'\nBest epoch: {best_epoch} with loss: {valid_loss_min:.2f} and acc: {100 * valid_acc:.2f}%')
-    history = pd.DataFrame(history, columns=['train_loss', 'valid_loss', 'train_acc', 'valid_acc'])
-    return model, history
-model, history = train(
-    model,
-    criterion,
-    optimizer,
-    train_loader,
-    val_loader,
-    save_location='./natural_images_resnet.pt',
-    early_stop=5,
-    n_epochs=10,
-    print_every=2)
+class GradCAM:
+    def __init__(self, model, feature_layer):
+        self.model = model
+        self.feature_layer = feature_layer
+        self.model.eval()
+        self.feature_grad = None
+        self.feature_map = None
+        self.hooks = []
+        # 最終層逆伝播時の勾配を記録する
+        def save_feature_grad(module, in_grad, out_grad):
+            self.feature_grad = out_grad[0]
+        self.hooks.append(self.feature_layer.register_backward_hook(save_feature_grad))
+        # 最終層の出力 Feature Map を記録する
+        def save_feature_map(module, inp, outp):
+            self.feature_map = outp[0]
+        self.hooks.append(self.feature_layer.register_forward_hook(save_feature_map))
+    def forward(self, x):
+        return self.model(x)
+    def backward_on_target(self, output, target):
+        self.model.zero_grad()
+        one_hot_output = torch.zeros([1, output.size()[-1]])
+        one_hot_output[0][target] = 1
+        output.backward(gradient=one_hot_output, retain_graph=True)
+    def clear_hook(self):
+        for hook in self.hooks:
+            hook.remove()
+path = "/Users/ora/Desktop/2019_33 ①.jpg"
+VISUALIZE_SIZE = (300, 200)
+image = Image.open(path)
+image.thumbnail(VISUALIZE_SIZE, Image.ANTIALIAS)
+plt.imshow(image)
+image_orig_size = image.size # (W, H)
+test_image_tensor = image_transforms['test'](image)
+test_image_tensor = test_image_tensor.unsqueeze(0)
+device = torch.device("cuda")
+model = models.resnet50(pretrained=False)
+n_classes = 2
+num_ftrs = model.fc.in_features
+model.fc = nn.Linear(num_ftrs, n_classes)
+model.to(device)
+model.eval()
+from collections import OrderedDict
+import torch
+checkpoint=torch.load('./natural_images_resnet.pt')
+state_dict=checkpoint
+new_state_dict=OrderedDict()
+model.load_state_dict(state_dict)
+#############GradCamによる可視化
+grad_cam = GradCAM(model, feature_layer=list(model.layer4.modules())[26])
+#画像をGradcamに入力
+model_output = grad_cam.forward(test_image_tensor)
+if len(model_output) == 1:
+    target = model_output.argmax(1).item()
+    grad_cam.backward_on_target(model_output, target)
+# Get feature gradient
+feature_grad = grad_cam.feature_grad.data.numpy()[0]
+# Get weights from gradient
+weights = np.mean(feature_grad, axis=(1, 2))  # Take averages for each gradient
+# Get features outputs
+feature_map = grad_cam.feature_map.data.numpy()
+grad_cam.clear_hook()
+cam = np.sum((weights * feature_map.T), axis=2).T
+cam = np.maximum(cam, 0)  # apply ReLU to cam
+cam = cv2.resize(cam, VISUALIZE_SIZE)
+cam = (cam - np.min(cam)) / (np.max(cam) - np.min(cam))  # Normalize between 0-1
+cam = np.uint8(cam * 255)  # Scale between 0-255 to visualize
+activation_heatmap = np.uint8(cv2.applyColorMap(cam, cv2.COLORMAP_JET))
+activation_heatmap = cv2.cvtColor(activation_heatmap, cv2.COLOR_BGR2RGB)  #色反転
+plt.imshow(activation_heatmap)
+org_img = np.asarray(image.resize(VISUALIZE_SIZE))
+intensity = 0.4
+img_with_heatmap = cv2.addWeighted(activation_heatmap, intensity, org_img, 1, 0)
+org_img = cv2.resize(org_img, image_orig_size)
+img_with_heatmap = cv2.resize(img_with_heatmap, image_orig_size)
+plt.figure(figsize=(10,5))
+plt.subplot(1,2,1)
+plt.imshow(org_img)
+plt.xticks(color="None")
+plt.yticks(color="None")
+plt.tick_params(length=0)
+plt.subplot(1,2,2)
+plt.imshow(img_with_heatmap)
+plt.xticks(color="None")
+plt.yticks(color="None")
+plt.tick_params(length=0)
+plt.show()
+```