深度学习使用问题
LoveWeeknd
不积跬步无以至千里不积小流无以成江海
展开
-
faster-rcnn tensorflow config.py 默认参数说明
文件位置:\lib\config\config.py1、修改训练多少次时保存一次模型tf.app.flags.DEFINE_integer('snapshot_iterations', 5000, "Iteration to take snapshot")修改snapshot_iterations参数,默认是5000,改成自己想要的数字即可2、修改训练总的次数tf.app....原创 2018-07-31 17:47:54 · 1919 阅读 · 1 评论 -
Faster-Rcnn-TF 输入图像尺寸变换
Faster-Rcnn本身对于采集的原图像没有要求,但是作为输入放入网络训练的话就必须限制图片的大小,一般Faster-Rcnn对于输入图像的大小限制规则是:限制最小边为600,最大边为1000,对于输入图像优先考虑最大边的限制代码:./lib/utils/blob.pydef prep_im_for_blob(im, pixel_means, target_size, max_size...原创 2018-09-05 17:54:07 · 9574 阅读 · 3 评论 -
ValueError: Variable vgg_16/conv1/conv1_1/weights already exists, disallowed
参考链接:https://stackoverflow.com/questions/44978210/valueerror-variable-vgg-16-conv1-conv1-1-weights-already-exists-disallowedhttps://bbs.csdn.net/topics/392277761问题描述:在windows端使用Flask+Apache+WS...原创 2018-10-29 14:59:20 · 3749 阅读 · 2 评论 -
ValueError: Error when checking input: expected input_image_meta to have shape (None, 14) but got ar
在跑maskrcnn的时候出现以下错误:Traceback (most recent call last): File "/home/ubuntu/DNN_Projection/Mask_RCNN--Training/samples/nucleus/nucleus.py", line 483, in <module> train(model, args.dataset,...原创 2018-11-08 14:02:11 · 9378 阅读 · 5 评论 -
ValueError: Tensor Tensor(“mrcnn_detection/Reshape_1:0“, shape=(1, 400, 6), dtype=float32) is not an
在使用mask-rcnn配合flask使用的时候出现了以下错误:Traceback (most recent call last): File "/home/ubuntu/anaconda3/envs/tensorflow1.3/lib/python3.6/site-packages/flask/app.py", line 2292, in wsgi_app response =...原创 2018-11-09 16:35:59 · 3903 阅读 · 1 评论 -
ValueError: Dimension 1 in both shapes must be equal, but are 8 and 324 for ‘Assign_376‘ (op: ‘Assig
使用Mask-RCNN测试细胞数据集的时候,出现了以下错误:Loading weights ../../path/to/weights.h5Traceback (most recent call last): File "/home/ubuntu/anaconda3/envs/tensorflow1.3/lib/python3.6/site-packages/tensorflow/p...原创 2018-10-30 15:33:49 · 6703 阅读 · 9 评论