l1uw3n

train all nan?

8

I use ：python train.py --batch-size 16 --img 512 512 --data person.yaml --cfg yolov4-p5.yaml --weights yolov4-p5.pt --sync-bn --device 1 --name yolov4-p5-tune --hyp 'data/hyp.finetune.yaml' --epochs 450 --resume result: 

请问如何加载一次模型预测多张图片？求助

1

`with tf.Graph().as_default(): with tf.Session().as_default() as sess: with open(FLAGS.image_file+kindList[0], 'rb') as img: if FLAGS.image_file.lower().endswith('png'): image = sess.run(tf.image.decode_png(img.read())) else: image = sess.run(tf.image.decode_jpeg(img.read())) height = image.shape[0] width = image.shape[1] image_preprocessing_fn, _ = preprocessing_factory.get_preprocessing(FLAGS.loss_model,is_training=False)...

Check failed: top_shape[j] == bottom[i]->shape(j) (24 vs. 26) All inputs must have the same shape, except at concat_axis

3


F1008 09:26:58.039983 13233 layer.hpp:367] Check failed: ExactNumTopBlobs() == top.size() (2 vs. 1)

1

F1008 09:26:58.039983 13233 layer.hpp:367] Check failed: ExactNumTopBlobs() == top.size() (2 vs. 1) VideoData Layer produces 2 top blob(s) as output. *** Check failure stack trace: *** @ 0x7f4f411f45b4 google::LogMessage::Fail() @...

how can I apply c3d to engineering？

4

Dear author, how can I apply c3d to engineering？ can I give some feasible suggestions? I can't package success using caffe's classification.cpp. @dutran

/usr/lib64/libgdk-x11-2.0.so.0：对‘XRRFreeMonitors’未定义的引用 /usr/lib64/libgdk-x11-2.0.so.0：对‘XRRGetMonitors’未定义的引用 /usr/lib64/libgdk-x11-2.0.so.0：对‘XRRFreeMonitors’未定义的引用 /usr/lib64/libgdk-x11-2.0.so.0：对‘XRRGetMonitors’未定义的引用 collect2: 错误：ld 返回 1 collect2: 错误：ld 返回 1 make: *** [.build_release/tools/convert_imageset.bin] 错误 1 make: *** 正在等待未完成的任务.... make: *** [.build_release/tools/device_query.bin] 错误 1 /usr/lib64/libgdk-x11-2.0.so.0：对‘XRRFreeMonitors’未定义的引用 /usr/lib64/libgdk-x11-2.0.so.0：对‘XRRGetMonitors’未定义的引用 /usr/lib64/libgdk-x11-2.0.so.0：对‘collect2: 错误：ld 返回...

Data resolution issue

1

I would like to download the SWOTL_L2-NALT.IGDR_2.0 data. After reading the data introduction, I learned that the spatial resolution of the data is 300 meters. May I ask if the...