Mobilenet-ssd-keras

Mobilenet-ssd-keras copied to clipboard

in order to load the pre trained model with the weights given in your repository , i also need the config file that is the architecture of the model to...

Avaneesh-S

Working fine for 3 batches in first iteration after that the loss was becoming Nan or inf.Can anyone had faced a similar issue or know where the issue is please...

ManishKakarla

Error while concatenating mbox_conf_softmax, mbox_loc, mbox_priorbox

5

Hi, Sorry to bother you, I am stuck on this : ValueError: A `Concatenate` layer requires inputs with matching shapes except for the concat axis. Got inputs shapes: [(None, 2268,...

amapic

Hi, I'm working with your code but i cannot obtain the specified mAP. I obtain 60.1% approximately by using converted_model.h5 weights file. Second the links specified to download the weights...

ManoniLo

ValueError when building

1

Hi, I'm experimenting with your repository but the training stops with error, raising this exception: ``` File "/home/davidecremona/PycharmProjects/Mobilenet-ssd-keras/training/drb_train_mobilenet_ssd.py", line 262, in train(args) File "/home/davidecremona/PycharmProjects/Mobilenet-ssd-keras/training/drb_train_mobilenet_ssd.py", line 242, in train callbacks=callbacks File...

davideCremona

The web page of the mobilenet_v1.h5 is 404. Can you provide another link or email me the weight file?My email is [email protected],thanks.

wuchenxi118

please, what parameters are needed for optimal forecast of the model in BatchGenerator train_dataset.generate(batch_size=batch_size, shuffle=True, train=True, ssd_box_encoder=ssd_box_encoder, convert_to_3_channels=True, equalize=True, brightness=(0.5, 2, 0.5), flip=0.5, translate=False, scale=False, max_crop_and_resize=(img_height, img_width, 1, 3), #...

Artem921

 when i run the training_mobilenet_ssd.py, the issue occured. how could i resolve it?

liguilan1227

when loading my training weights the same tensor is predicted model.load_weights('/home/artem/object detection/virtual/Mobilenet-ssd-keras/MobilenetWeights/mobilenet.h5', by_name=True,skip_mismatch=True) y_pred = model.predict(input_images) print(y_pred) [[[0.25 0.25 0.25 ... 0.1 0.2 0.2 ] [0.25 0.25 0.25 ... 0.1...

Artem921

in file: infer_mobilenet_ssd.py y_pred_decoded = decode_y(y_pred, confidence_thresh=0.25, iou_threshold=0.45, top_k=100, input_coords='centroids', normalize_coords=True, img_height=img_height, img_width=img_width) print(y_pred_decoded) out: [ [ ] ]

Artem921