maxlchina

loss can't converge and all detect results are 15(person)

2

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?

ValueError: No data files found in ./VOCdevkit/VOC2007/voc_2007_test_*.tfrecord

10

hi，when I run the eval_ssd_network.py, it gave this error: Traceback (most recent call last): File "eval_ssd_network.py", line 346, in tf.app.run() File "/home/maxl/anaconda3/lib/python3.5/site-packages/tensorflow/python/platform/app.py", line 48, in run _sys.exit(main(_sys.argv[:1] + flags_passthrough)) File...

TypeError: l2_normalize() got an unexpected keyword argument 'axis'

3

hello,when i run the file SSD_training.ipynb, it give this erro: --------------------------------------------------------------------------- TypeError Traceback (most recent call last) in () ----> 1 model = SSD300(input_shape, num_classes=NUM_CLASSES) 2 model.load_weights('weights_SSD300.hdf5', by_name=True) /home/maxl/ssd_keras-master/ssd.py in...