First time training, HTTP Error 403: Forbidden?!

[eduardohem]

loading annotations into memory...
Done (t=10.57s)
creating index...
index created!
loading annotations into memory...
Done (t=0.33s)
creating index...
index created!
Downloading: "http://storage.googleapis.com/public-models/efficientnet/efficientnet-b0-355c32eb.pth" to /home/itandroids/.cache/torch/checkpoints/efficientnet-b0-355c32eb.pth
Traceback (most recent call last):
File "train.py", line 335, in
main()
File "train.py", line 331, in main
main_worker(args.gpu, ngpus_per_node, args)
File "train.py", line 232, in main_worker
D_class=EFFICIENTDET[args.network]['D_class']
File "/home/itandroids/Desktop/eficientedet/toandao/models/efficientdet.py", line 33, in init
self.backbone = EfficientNet.from_pretrained(MODEL_MAP[network])
File "/home/itandroids/Desktop/eficientedet/toandao/models/efficientnet.py", line 243, in from_pretrained
model, model_name, load_fc=(num_classes == 1000))
File "/home/itandroids/Desktop/eficientedet/toandao/models/utils.py", line 319, in load_pretrained_weights
state_dict = model_zoo.load_url(url_map[model_name])
File "/home/itandroids/Desktop/eficientedet/toandao/lib/python3.6/site-packages/torch/hub.py", line 492, in load_state_dict_from_url
download_url_to_file(url, cached_file, hash_prefix, progress=progress)
File "/home/itandroids/Desktop/eficientedet/toandao/lib/python3.6/site-packages/torch/hub.py", line 391, in download_url_to_file
u = urlopen(url)
File "/usr/lib/python3.6/urllib/request.py", line 223, in urlopen
return opener.open(url, data, timeout)
File "/usr/lib/python3.6/urllib/request.py", line 532, in open
response = meth(req, response)
File "/usr/lib/python3.6/urllib/request.py", line 642, in http_response
'http', request, response, code, msg, hdrs)
File "/usr/lib/python3.6/urllib/request.py", line 570, in error
return self._call_chain(*args)
File "/usr/lib/python3.6/urllib/request.py", line 504, in _call_chain
result = func(*args)
File "/usr/lib/python3.6/urllib/request.py", line 650, in http_error_default
raise HTTPError(req.full_url, code, msg, hdrs, fp)
urllib.error.HTTPError: HTTP Error 403: Forbidden

[josh-marsh]

same issue, but in load_pretrained_weights. When you actually try and open the weights link you get:

Anonymous caller does not have storage.objects.get access to public-models/efficientnet/efficientnet-b0-355c32eb.pth.

[HunbeomBak]

i have a same problem when run demo.py on pytorch-1.4.0, torchvisoin 0.5.0.

i use command
'python demo.py --threshold 0.5 --iou_threshold 0.5 --score --weight pre_trained/checkpoint_VOC_efficientdet-d0_268.pth --file_name demo.png'

i downloaded pre-traiend model form google drive, but demo.py tried download pre-trained, and occurred same problem.

below is error.

Load pretrained Model
Downloading: "http://storage.googleapis.com/public-models/efficientnet/efficientnet-b0-355c32eb.pth" to /home/jovyan/.cache/torch/checkpoints/efficientnet-b0-355c32eb.pth
Traceback (most recent call last):
  File "demo.py", line 174, in <module>
    detect = Detect(weights=args.weight)
  File "demo.py", line 61, in __init__
    is_training=False
  File "/home/jovyan/work/object_detection/EfficientDet.Pytorch/models/efficientdet.py", line 33, in __init__
    self.backbone = EfficientNet.from_pretrained(MODEL_MAP[network])
  File "/home/jovyan/work/object_detection/EfficientDet.Pytorch/models/efficientnet.py", line 243, in from_pretrained
    model, model_name, load_fc=(num_classes == 1000))
  File "/home/jovyan/work/object_detection/EfficientDet.Pytorch/models/utils.py", line 319, in load_pretrained_weights
    state_dict = model_zoo.load_url(url_map[model_name])
  File "/opt/conda/lib/python3.7/site-packages/torch/hub.py", line 495, in load_state_dict_from_url
    download_url_to_file(url, cached_file, hash_prefix, progress=progress)
  File "/opt/conda/lib/python3.7/site-packages/torch/hub.py", line 394, in download_url_to_file
    u = urlopen(url)
  File "/opt/conda/lib/python3.7/urllib/request.py", line 222, in urlopen
    return opener.open(url, data, timeout)
  File "/opt/conda/lib/python3.7/urllib/request.py", line 531, in open
    response = meth(req, response)
  File "/opt/conda/lib/python3.7/urllib/request.py", line 641, in http_response
    'http', request, response, code, msg, hdrs)
  File "/opt/conda/lib/python3.7/urllib/request.py", line 569, in error
    return self._call_chain(*args)
  File "/opt/conda/lib/python3.7/urllib/request.py", line 503, in _call_chain
    result = func(*args)
  File "/opt/conda/lib/python3.7/urllib/request.py", line 649, in http_error_default
    raise HTTPError(req.full_url, code, msg, hdrs, fp)
urllib.error.HTTPError: HTTP Error 403: Forbidden

[Erotemic]

Looks like the pretrained weight urls have gone bad.

[jdubpark]

Replace the url_map in model/utils.py with:

url_map = {
    'efficientnet-b0': 'https://github.com/lukemelas/EfficientNet-PyTorch/releases/download/1.0/efficientnet-b0-355c32eb.pth',
    'efficientnet-b1': 'https://github.com/lukemelas/EfficientNet-PyTorch/releases/download/1.0/efficientnet-b1-f1951068.pth',
    'efficientnet-b2': 'https://github.com/lukemelas/EfficientNet-PyTorch/releases/download/1.0/efficientnet-b2-8bb594d6.pth',
    'efficientnet-b3': 'https://github.com/lukemelas/EfficientNet-PyTorch/releases/download/1.0/efficientnet-b3-5fb5a3c3.pth',
    'efficientnet-b4': 'https://github.com/lukemelas/EfficientNet-PyTorch/releases/download/1.0/efficientnet-b4-6ed6700e.pth',
    'efficientnet-b5': 'https://github.com/lukemelas/EfficientNet-PyTorch/releases/download/1.0/efficientnet-b5-b6417697.pth',
    'efficientnet-b6': 'https://github.com/lukemelas/EfficientNet-PyTorch/releases/download/1.0/efficientnet-b6-c76e70fd.pth',
    'efficientnet-b7': 'https://github.com/lukemelas/EfficientNet-PyTorch/releases/download/1.0/efficientnet-b7-dcc49843.pth',
}

These links work.

[dscarmo]

Same problem. Just created a pull request to fix the links.