SSD-Tensorflow
SSD-Tensorflow copied to clipboard
balancap
Single Shot MultiBox Detector in TensorFlow
in train_ssd_.py we have batch size and max_num of steps for training . but if we dont set max_num of steps then how many epoch my model will trained?
`INFO:tensorflow:Restoring parameters from /content/SSD-Tensorflow-On-Custom-Dataset/VOC2007_/log/model.ckpt-22050 --------------------------------------------------------------------------- InvalidArgumentError Traceback (most recent call last) /usr/local/lib/python3.7/dist-packages/tensorflow_core/python/client/session.py in _do_call(self, fn, *args) 1364 try: -> 1365 return fn(*args) 1366 except errors.OpError as e: 8 frames /usr/local/lib/python3.7/dist-packages/tensorflow_core/python/client/session.py...
I have problems when i run the eval_ssd_network.py in my PC.(python3.7) my eval_ssd_network.sh is presented as follows: python eval_ssd_network.py --eval_dir=C:\Users\Alice\Desktop\Program\SSD-Tensorflow-master\eval_result\eval_1\ --dataset_dir=C:\Users\Alice\Desktop\Program\SSD-Tensorflow-master\test_tf\ --dataset_name=pascalvoc_2007 --dataset_split_name=test --model_name=ssd_300_vgg --checkpoint_path=C:\Users\Alice\Desktop\Program\SSD-Tensorflow-master\checkpoints\ssd_300_vgg.ckpt --batch_size=1 problem: C:\Users\Alice\Desktop\Program\SSD-Tensorflow-master>python eval_ssd_network.py --eval_dir=C:\Users\Alice\Desktop\Program\SSD-Tensorflow-master\eval_result\eval_1\...
# Description tl;dr: The pre-trained SSD checkpoint has a huge loss while training on the **VOC2007 train + val** dataset and it doesn't seem to be anywhere near convergence. I...
I am training my own data based on pre-trained checkpoint vgg16.chkp. My dataset is 1500 pictures，two classes contain 0：background and 1：myObject，my batch=50 **why loss converge so slow？！** `INFO:tensorflow:Recording summary at...
Your work is very nice. I have a question about training. I trained voc_2007_train. I got a below total loss.  Total loss does not converge. When I use caffe...
I changed the backbone net from VGG to mobilenetV2, but loss can't converge. when test the model in pre, i found all results are 15(person), what's wrong with this work?
I want to get a plot which is showing losses and mAP. How can I do? Please, help me
在加载自己训练的模型时,出现错误 InvalidArgumentError : Assign requires shapes of both tensors to match. lhs shape= [126] rhs shape= [12]. 希望能得到解答，不知道为啥。谢了~！
2018-07-28 10:35:04.192687: W c:\users\user\source\repos\tensorflow\tensorflow\core\framework\op_kernel.cc:1318] OP_REQUIRES failed at conv_ops.cc:673 : Resource exhausted: OOM when allocating tensor with shape[16,64,300,300] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc INFO:tensorflow:Error reported to Coordinator: ,...
