yolov3-tf2

yolov3-tf2 copied to clipboard

训练过程中的参数调整，能否明确描述一下啊

jiangxinufo

(yolov3-tf2-cpu) (venv) M:\MachineLearning\yolov3-tf2>python train.py --dataset ./data/voc2007_train_stone.tfrecord --val_dataset ./data/voc2007_val_stone.tfrecord --classes ./data/stone.names --num_classes 1 --mode fit --transfer dark net --batch_size 4 --epochs 20 --weights ./checkpoints/yolov3.tf --weights_num_classes 80 Traceback (most recent call last):...

jiangxinufo

ValueError: Error when checking input: expected input to have 4 dimensions, but got array with shape (416, 416, 3)

jiangxinufo

Custom Dataset Shape Incorrect

1

I'm loading in my own data via the tfrecords file. First, I am getting the error: ` ValueError: Input 0 is incompatible with layer yolov3: expected shape=(None, 416, 416, 3),...

k-macdonald

gokulsoman15

Custom Training Help

1

I'm training on a 1 class dataset that has relatively small objects. When training I noticed that the loss on Output 3 is huge compared to the others but eventually...

ahndroo

Hallo, I want to ask that why my video is detacted successfully only in the beginning and then all labelling disapperar. Thank you in advance.

Linkwan999

Transform own darknet weights for this model

2

I have received a yolov3 model or the weights of a yolov3 model that was trained with darknet from AlexeyAB. If I now perform the transformation of the weights I...

johnny-mueller

scaling bounding box

1

when we generate tf record, bounding box is scaled based on original image size. When we load image and resize in load_tfrecord_dataset method, i suppose bounding box also needs to...

VeeranjaneyuluToka

How about siwsh or mish activation instead of LeakyRelu activation?

2

pake2070