关于数据集的放置问题 about attentive-gan-derainnet HOT 14 CLOSED

@duguangmeiyu 我好像放了放置示例数据集存放格式,等我有空了整理一下放上去。==！

from attentive-gan-derainnet.

好的好的非常感谢，那请问这个运行的报错问题您遇到过么。。。有没有什么解决的办法。。。非常感谢！！！

from attentive-gan-derainnet.

@duguangmeiyu 这个运行报错就是因为你没有按照我的规则组织训练数据, 你重新pull一下代码然后看一下data里面的training example data然后按照那个例子的样子重新组织一下你的训练数据就好了

from attentive-gan-derainnet.

非常感谢您对我问题的解答，但是我又遇到了新的问题= =！
File "/home/liuguangyu/attentive-gan-derainnet-master/tools/data_provider.py", line 130, in next_batch
return self.next_batch(batch_size)
File "/home/liuguangyu/attentive-gan-derainnet-master/tools/data_provider.py", line 130, in next_batch
return self.next_batch(batch_size)
File "/home/liuguangyu/attentive-gan-derainnet-master/tools/data_provider.py", line 128, in next_batch
self._random_dataset()
File "/home/liuguangyu/attentive-gan-derainnet-master/tools/data_provider.py", line 61, in _random_dataset
random_idx = np.random.permutation(len(self._gt_img_list))
File "mtrand.pyx", line 4907, in mtrand.RandomState.permutation
File "mtrand.pyx", line 4841, in mtrand.RandomState.shuffle
RuntimeError: maximum recursion depth exceeded in cmp
不知道您有没有对这个问题的应对方法，再次非常感谢！！

from attentive-gan-derainnet.

@duguangmeiyu 可以截图你的训练数据集文件夹 和你的train.txt文件

from attentive-gan-derainnet.

额。。。。这个问题解决了。。。然后又出现问题了。。。我自己都尴尬了。。。谢谢大佬！！
VGG16 Network init complete
2018-09-18 08:27:01.787846: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
I0918 08:27:02.986565 17810 train_model.py:136] Global configuration is as follows:
I0918 08:27:02.999047 17810 train_model.py:137] {'TEST': {'TF_ALLOW_GROWTH': True, 'IMG_HEIGHT': 240, 'BATCH_SIZE': 1, 'GPU_MEMORY_FRACTION': 0.8, 'IMG_WIDTH': 360}, 'TRAIN': {'LEARNING_RATE': 0.002, 'IMG_WIDTH': 360, 'BATCH_SIZE': 1, 'EPOCHS': 200010, 'IMG_HEIGHT': 240, 'TF_ALLOW_GROWTH': True, 'GPU_MEMORY_FRACTION': 0.95}}
I0918 08:27:06.023253 17810 train_model.py:145] Training from scratch
Traceback (most recent call last):
File "tools/train_model.py", line 212, in
train_model(args.dataset_dir, weights_path=args.weights_path)
File "tools/train_model.py", line 170, in train_model
gt_imgs, label_imgs, mask_imgs = train_dataset.next_batch(CFG.TRAIN.BATCH_SIZE)
File "/home/liuguangyu/attentive-gan-derainnet-master/tools/data_provider.py", line 143, in next_batch
gt_image = cv2.resize(gt_image, (CFG.TRAIN.IMG_WIDTH, CFG.TRAIN.IMG_HEIGHT))
cv2.error: OpenCV(3.4.3) /io/opencv/modules/imgproc/src/resize.cpp:4044: error: (-215:Assertion failed) !ssize.empty() in function 'resize'

from attentive-gan-derainnet.

@duguangmeiyu Debug先看下一下这个gt_img你正确读入了么 这个应该是你没有读进去图像 应该是你的train.txt写入的图像路径不对

from attentive-gan-derainnet.

attentive-gan-derainnet-master/data/training_data_example/gt_label/0_clean.png attentive-gan-derainnet-master/data/training_data_example/data/0_rain.png
attentive-gan-derainnet-master/data/training_data_example/gt_label/1_clean.png attentive-gan-derainnet-master/data/training_data_example/data/1_rain.png
attentive-gan-derainnet-master/data/training_data_example/gt_label/2_clean.png attentive-gan-derainnet-master/data/training_data_example/data/2_rain.png
attentive-gan-derainnet-master/data/training_data_example/gt_label/3_clean.png attentive-gan-derainnet-master/data/training_data_example/data/3_rain.png
这是train.txt里的路径。。感觉没问题的啊= =！

from attentive-gan-derainnet.

@duguangmeiyu 你的脚本执行目录应该是在attentive-gan-derainnet-master这一级目录下 所以你的数据路径相对路径应该是从data开始。为了避免错误建议直接写绝对路径.

from attentive-gan-derainnet.

通了通了！！！谢谢大佬！！！！爱你！！！！1

from attentive-gan-derainnet.

@duguangmeiyu 不客气

from attentive-gan-derainnet.

Since no further question about it I will close it

from attentive-gan-derainnet.

@duguangmeiyu 请问你数据集在哪找的呀，能不能发个链接或者加我qq1129620314发我，感谢

from attentive-gan-derainnet.

@duguangmeiyu 请问你数据集在哪找的呀，能不能发个链接或者加我qq1129620314发我，感谢

同求

from attentive-gan-derainnet.