TypeError: Failed to convert object of type <class 'tuple'> to Tensor. Contents: (None, 128, 128, 2, 64). Consider casting elements to a supported type. There is no problem with the other models I use.

I'm using SimplePose models and train them with my custom dataset generator with this snippet:

print(f'Tensror Flow version: {tf.__version__}')
tf.keras.backend.clear_session()

BATCH_SIZE=64
NUM_KEYPOINTS=14
IMAGE_RES=128
HEATMAP_RES=32

net = tf2cv_get_model("simplepose_mobile_mobilenetv3_large_w1_coco", 
                      pretrained_backbone=True,
                      keypoints=NUM_KEYPOINTS, 
                      return_heatmap=True)

net.build(input_shape=(BATCH_SIZE, IMAGE_RES, IMAGE_RES, 3))
net.heatmap_max_det.build((BATCH_SIZE, HEATMAP_RES, HEATMAP_RES, NUM_KEYPOINTS))
net.summary()
net.compile(optimizer=tf.keras.optimizers.Adam(lr=5e-4), 
            loss=tf.keras.losses.mean_squared_error)

history = net.fit_generator(
  generator=train_data,
  validation_data=valid_data,
  epochs=15
)

And that works or not depending on the model type I choose. If I use any non mobile model ( simplepose_resnet18_coco for example) then everything works, the network trains and predicts accurate results. Whereas if use any mobile model like simplepose_mobile_mobilenetv3_large_w1_coco or simplepose_mobile_resnet18_coco, the above code will break with the following error:

Tensror Flow version: 2.1.0
Downloading /root/.tensorflow/models/mobilenetv3_large_w1-0769-f66596ae.tf2.h5.zip from https://github.com/osmr/imgclsmob/releases/download/v0.0.422/mobilenetv3_large_w1-0769-f66596ae.tf2.h5.zip...
Model: "simple_pose_mobile"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
backbone (Sequential)        multiple                  2996352   
_________________________________________________________________
decoder (Sequential)         multiple                  1798080   
_________________________________________________________________
heatmap_max_det (HeatmapMaxD multiple                  0         
=================================================================
Total params: 4,794,432
Trainable params: 4,768,240
Non-trainable params: 26,192
_________________________________________________________________

TypeError: in converted code:

    /usr/local/lib/python3.6/dist-packages/tf2cv/models/simpleposemobile_coco.py:94 call  *
        heatmap = self.decoder(x, training=training)
    /tensorflow-2.1.0/python3.6/tensorflow_core/python/keras/engine/base_layer.py:773 __call__
        outputs = call_fn(cast_inputs, *args, **kwargs)
    /usr/local/lib/python3.6/dist-packages/tf2cv/models/common.py:2016 call  *
        x = self.pix_shuffle(x)
    /tensorflow-2.1.0/python3.6/tensorflow_core/python/keras/engine/base_layer.py:773 __call__
        outputs = call_fn(cast_inputs, *args, **kwargs)
# .... 

    TypeError: Failed to convert object of type <class 'tuple'> to Tensor. Contents: (None, 4, 4, 128, 4). Consider casting elements to a supported type.

It looks to me like the net output is in some unexpected format. See this gist for the full output: https://gist.github.com/grin/d1a9836aca5ca462dbb03527246ba941

What could be causing this error? Am I missing some crucial configuration for mobile models? I would expect the two APIs work similarly.

Thank you

I am trying to use pspnet_resnetd101b_voc as follows:

sample_batch_size = 1
channel = 3
height, width = 224.224
dummy_input = torch.randn(sample_batch_size, channel, height, width)
out = pspnet_resnetd101b_voc(dummy_input)

But I get following error: Expected more than 1 value per channel when training, got input size torch.Size([1, 512, 1, 1])

What are the right data format for this model or similar as pspnet_resnetd101b_coco?.

Note: With Imagenet pretrained model resnetd101b works fine.

checkpoint = ModelCheckpoint('./gdrive/My Drive/MLAI_files/project-images/Full_Dataset/squeezenext_weights.{epoch:02d}-{val_loss:.2f}.hdf5', monitor='val_loss', save_best_only=True, mode='min') callbacks_list = [checkpoint] hist = new_model.fit_generator(generator = my_gen(train_generator), steps_per_epoch = STEP_SIZE_TRAIN, validation_data = my_gen(valid_generator), validation_steps = STEP_SIZE_VALID, epochs = 3, callbacks = callbacks_list)

Epoch 1/3 38/377 [==>...........................] - ETA: 3:54 - loss: 2.0859 - acc: 0.2188/usr/local/lib/python3.6/dist-packages/PIL/Image.py:914: UserWarning: Palette images with Transparency expressed in bytes should be converted to RGBA images 'to RGBA images') 117/377 [========>.....................] - ETA: 2:35 - loss: 2.0482 - acc: 0.2356/usr/local/lib/python3.6/dist-packages/PIL/TiffImagePlugin.py:742: UserWarning: Corrupt EXIF data. Expecting to read 4 bytes but only got 0. warnings.warn(str(msg)) 377/377 [==============================] - 221s 586ms/step - loss: 2.0704 - acc: 0.2301 - val_loss: 5.2917 - val_acc: 0.2820

TypeError Traceback (most recent call last) in () 4 validation_steps = STEP_SIZE_VALID, 5 epochs = 3, ----> 6 callbacks = callbacks_list)

12 frames /usr/local/lib/python3.6/dist-packages/keras/engine/saving.py in get_json_type(obj) 89 return obj.name 90 ---> 91 raise TypeError('Not JSON Serializable: %s' % (obj,)) 92 93 from .. import version as keras_version

TypeError: Not JSON Serializable: <module 'tensorflow' from '/usr/local/lib/python3.6/dist-packages/tensorflow/init.py'>

Hello, When the PSPNet pre-trained model is used, the output is a tuple of 2 tensors. Can someone clarify what they are and how to achieve 1 output among them such that computation time can be saved?

net = get_model('pspnet_resnetd101b_cityscapes',pretrained_backbone=True,pretrained = True) yp = net(X) yp.size()

This throws an error: AttributeError Traceback (most recent call last) in 1 yp = net(X) # model outputs 2 different learning rates ----> 2 yp.size()

AttributeError: 'tuple' object has no attribute 'size'

Hello,

I am using fastai to implement some computer vision project. I recently stumbled across this repo and found it a great add-on to my arsenal of models. However, I am trying to create a pretrained DPN98. I found someone in the fastai repo that is having a similar problem with Alexnet (though they didn't specify where they got the model from) here. I also tried DPN 68 with same result.

The traceback I get looks like this:

---------------------------------------------------------------------------
Exception                                 Traceback (most recent call last)
<ipython-input-21-096da45f530c> in <module>
      1 # Setup the model and
----> 2 learn = cnn_learner(data, dpn98, metrics=[precision, accuracy], callback_fns=ShowGraph)
      3 learn.model_dir='/kaggle/working/'
      4 learn.freeze()

/opt/conda/lib/python3.6/site-packages/fastai/vision/learner.py in cnn_learner(data, base_arch, cut, pretrained, lin_ftrs, ps, custom_head, split_on, bn_final, init, concat_pool, **kwargs)
     96     meta = cnn_config(base_arch)
     97     model = create_cnn_model(base_arch, data.c, cut, pretrained, lin_ftrs, ps=ps, custom_head=custom_head,
---> 98         bn_final=bn_final, concat_pool=concat_pool)
     99     learn = Learner(data, model, **kwargs)
    100     learn.split(split_on or meta['split'])

/opt/conda/lib/python3.6/site-packages/fastai/vision/learner.py in create_cnn_model(base_arch, nc, cut, pretrained, lin_ftrs, ps, custom_head, bn_final, concat_pool)
     84     body = create_body(base_arch, pretrained, cut)
     85     if custom_head is None:
---> 86         nf = num_features_model(nn.Sequential(*body.children())) * (2 if concat_pool else 1)
     87         head = create_head(nf, nc, lin_ftrs, ps=ps, concat_pool=concat_pool, bn_final=bn_final)
     88     else: head = custom_head

/opt/conda/lib/python3.6/site-packages/fastai/callbacks/hooks.py in num_features_model(m)
    118     sz = 64
    119     while True:
--> 120         try: return model_sizes(m, size=(sz,sz))[-1][1]
    121         except Exception as e:
    122             sz *= 2

/opt/conda/lib/python3.6/site-packages/fastai/callbacks/hooks.py in model_sizes(m, size)
    111     "Pass a dummy input through the model `m` to get the various sizes of activations."
    112     with hook_outputs(m) as hooks:
--> 113         x = dummy_eval(m, size)
    114         return [o.stored.shape for o in hooks]
    115 

/opt/conda/lib/python3.6/site-packages/fastai/callbacks/hooks.py in dummy_eval(m, size)
    106 def dummy_eval(m:nn.Module, size:tuple=(64,64)):
    107     "Pass a `dummy_batch` in evaluation mode in `m` with `size`."
--> 108     return m.eval()(dummy_batch(m, size))
    109 
    110 def model_sizes(m:nn.Module, size:tuple=(64,64))->Tuple[Sizes,Tensor,Hooks]:

/opt/conda/lib/python3.6/site-packages/fastai/callbacks/hooks.py in dummy_batch(m, size)
    101 def dummy_batch(m: nn.Module, size:tuple=(64,64))->Tensor:
    102     "Create a dummy batch to go through `m` with `size`."
--> 103     ch_in = in_channels(m)
    104     return one_param(m).new(1, ch_in, *size).requires_grad_(False).uniform_(-1.,1.)
    105 

/opt/conda/lib/python3.6/site-packages/fastai/torch_core.py in in_channels(m)
    261     for l in flatten_model(m):
    262         if hasattr(l, 'weight'): return l.weight.shape[1]
--> 263     raise Exception('No weight layer')
    264 
    265 class ModelOnCPU():

Exception: No weight layer

I'll include the proceeding code I have up to this point to help you get an idea of what environment I am running. Note, this is in Kaggle.

from fastai.vision import *
# For more models
!pip install pytorchcv
from pytorchcv.model_provider import get_model as ptcv_get_model

# Data augs
tfms = get_transforms()

# Get databunch to feed to the network
data = ImageDataBunch.from_folder(path, valid_pct=0.2, size = 1028, bs = 2, ds_tfms = tfms, padding_mode='zeros').normalize(imagenet_stats)

# Custom arch
def dpn98(pretrained=False):
    return ptcv_get_model("dpn98", pretrained=False).features

# Get custom precision metric
precision = Precision(pos_label = 0)

# Setup the model and 
learn = cnn_learner(data, dpn98, metrics=[precision, accuracy], callback_fns=ShowGraph)

Is there a good way to go about modifying the pre-trained models? I want to tweak the forward() function to return activations at a few layers. I'm going to be comparing between several CIFAR models so training them all myself isn't really viable.

Thanks!

hi, thank you for the great repository. The problem that I came to is that I cannot find a list of classes for which the tf2 models of imagenet1k were trained for. Also the website of imagenet is not very helpfull in that regard.

For example, how could I load an image, classify it and print the class label? An example for how to do this would be very helpful to add.

Hi,

I tried to use ImageNet classifier with a pretrained model SE-ResNext50. I added just a Softmax activation. It results in values with mean 0.01 and range about 0.005-0.02, which don't seem like proper softmax predictions. Actual results are incorrect.

If I change 1 line to use torchvision.models.resnet50, inference works like a charm: it detects dogs, cars, etc. Is there anything I'm missing? I'm using pytorchcv==0.0.45.

Btw, maybe you should add __version__ into the package.

Cheers!

Hi Thanks for such a brilliant work.

i was going to train a ghost net model on tf2 by train_tf2.py. And i used a tiny dataset at first which contains 78 images in training set and 40 for val and set epoch as 1, batch size as 4. But it seem cannot stop this single epoch. Let me show you in the code. I put some print and counter into the loop, like.

print(train_img_count)
 num_epochs = args.num_epochs
 print(num_epochs)
 for epoch in range(num_epochs):
     print(20) #meanless thing
     conuter= 0
     for images, labels in train_data:
         print(conuter)
         conuter+=1
         train_step(images, labels)
     print(16) #meanless thing

In this case, the terminal keep printing out the counter . Although it didn't throw any errors or excepts, it just keep runing. The counter is much bigger than the number of train images(300 vs 78). The terminal output going like

Found 78 images belonging to 2 classes.
Found 40 images belonging to 2 classes.
78             # train_img_count
1               # num_epochs
20            # that meanless number
0               #counter started from here
1
2
3
4
5
6
.......
300

Any idea about this?

The imagenet-pretrained model has 1000 classes, but when I only want to replace the last dense layer, I got the error. It looks like classes=1000 cannot be changed. I would suggest add some argument include_top=False just like in tf.keras.applications.ResNet50, which we can customize the last dense layer.

net = kecv_get_model("resnet50", pretrained=True, classes=100) https://github.com/osmr/imgclsmob/blob/4b01a0e635e54d08929d9b340e8d369f5add0275/keras_/kerascv/models/resnet.py#L223

AssertionError                            Traceback (most recent call last)
<ipython-input-26-c5cb45b6fa44> in <module>
----> 1 net = kecv_get_model("resnet50", pretrained=True, classes=100)

~/miniconda3/envs/tf114/lib/python3.6/site-packages/kerascv/model_provider.py in get_model(name, **kwargs)
    246     if name not in _models:
    247         raise ValueError("Unsupported model: {}".format(name))
--> 248     net = _models[name](**kwargs)
    249     return net

~/miniconda3/envs/tf114/lib/python3.6/site-packages/kerascv/models/resnet.py in resnet50(**kwargs)
    585         Location for keeping the model parameters.
    586     """
--> 587     return get_resnet(blocks=50, model_name="resnet50", **kwargs)
    588 
    589 

~/miniconda3/envs/tf114/lib/python3.6/site-packages/kerascv/models/resnet.py in get_resnet(blocks, bottleneck, conv1_stride, width_scale, model_name, pretrained, root, **kwargs)
    376             net=net,
    377             model_name=model_name,
--> 378             local_model_store_dir_path=root)
    379 
    380     return net

~/miniconda3/envs/tf114/lib/python3.6/site-packages/kerascv/models/model_store.py in download_model(net, model_name, local_model_store_dir_path)
    511         file_path=get_model_file(
    512             model_name=model_name,
--> 513             local_model_store_dir_path=local_model_store_dir_path))

~/miniconda3/envs/tf114/lib/python3.6/site-packages/kerascv/models/model_store.py in load_model(net, file_path, skip_mismatch)
    489             _load_weights_from_hdf5_group(
    490                 f=f,
--> 491                 layers=net.layers)
    492 
    493 

~/miniconda3/envs/tf114/lib/python3.6/site-packages/kerascv/models/model_store.py in _load_weights_from_hdf5_group(f, layers)
    391         weight_values = _preprocess_weights_for_loading(
    392             layer=layer,
--> 393             weights=weight_values)
    394         if len(weight_values) != len(symbolic_weights):
    395             raise ValueError('Layer #' + str(k) +

~/miniconda3/envs/tf114/lib/python3.6/site-packages/kerascv/models/model_store.py in _preprocess_weights_for_loading(layer, weights)
    346             weights[0] = np.transpose(weights[0], (2, 3, 0, 1))
    347     for i in range(len(weights)):
--> 348         assert (K.int_shape(layer.weights[i]) == weights[i].shape)
    349     return weights
    350 

AssertionError:

The simplepose_resnet18_coco pretrained weights cannot be loaded using pytorchcv.

How to reproduce

1. Create and activate a new environment

conda create -n avl_simplepose python=3.9
conda activate avl_simplepose

2. Install pytorchcv and torch packages (pip). Note: the exact torch install command may vary. I used the one from the official site for CUDA 11.6

pip install pytorchcv
pip3 install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu116

3. Make sure no .torch folder exists in the home directory (may not be needed to reproduce the issue).
4. Run the following commands (+log):

Python 3.9.13 | packaged by conda-forge | (main, May 27 2022, 16:58:50) 
[GCC 10.3.0] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import torch
>>> from pytorchcv.model_provider import get_model as ptcv_get_model
>>> 
>>> ptcv_get_model("simplepose_resnet18_coco", pretrained=True)
Downloading /home/lorenzo/.torch/models/simplepose_resnet18_coco-6631-7c3656b3.pth.zip from https://github.com/osmr/imgclsmob/releases/download/v0.0.455/simplepose_resnet18_coco-6631-7c3656b3.pth.zip...

Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/home/lorenzo/miniconda3/envs/prova_avl_simplepose/lib/python3.9/site-packages/pytorchcv/model_provider.py", line 1233, in get_model
    net = _models[name](**kwargs)
  File "/home/lorenzo/miniconda3/envs/prova_avl_simplepose/lib/python3.9/site-packages/pytorchcv/models/simplepose_coco.py", line 155, in simplepose_resnet18_coco
    return get_simplepose(backbone=backbone, backbone_out_channels=512, keypoints=keypoints,
  File "/home/lorenzo/miniconda3/envs/prova_avl_simplepose/lib/python3.9/site-packages/pytorchcv/models/simplepose_coco.py", line 129, in get_simplepose
    download_model(
  File "/home/lorenzo/miniconda3/envs/prova_avl_simplepose/lib/python3.9/site-packages/pytorchcv/models/model_store.py", line 827, in download_model
    load_model(
  File "/home/lorenzo/miniconda3/envs/prova_avl_simplepose/lib/python3.9/site-packages/pytorchcv/models/model_store.py", line 804, in load_model
    net.load_state_dict(pretrained_state)
  File "/home/lorenzo/miniconda3/envs/prova_avl_simplepose/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1667, in load_state_dict
    raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for SimplePose:
        Missing key(s) in state_dict: "backbone.0.conv.conv.weight", "backbone.0.conv.bn.weight", "backbone.0.conv.bn.bias", "backbone.0.conv.bn.running_mean", "backbone.0.conv.bn.running_var", "backbone.1.unit1.body.conv1.conv.weight", "backbone.1.unit1.body.conv1.bn.weight", "backbone.1.unit1.body.conv1.bn.bias", "backbone.1.unit1.body.conv1.bn.running_mean", "backbone.1.unit1.body.conv1.bn.running_var", "backbone.1.unit1.body.conv2.conv.weight", "backbone.1.unit1.body.conv2.bn.weight", "backbone.1.unit1.body.conv2.bn.bias", "backbone.1.unit1.body.conv2.bn.running_mean", "backbone.1.unit1.body.conv2.bn.running_var", "backbone.1.unit2.body.conv1.conv.weight", "backbone.1.unit2.body.conv1.bn.weight", "backbone.1.unit2.body.conv1.bn.bias", "backbone.1.unit2.body.conv1.bn.running_mean", "backbone.1.unit2.body.conv1.bn.running_var", "backbone.1.unit2.body.conv2.conv.weight", "backbone.1.unit2.body.conv2.bn.weight", "backbone.1.unit2.body.conv2.bn.bias", "backbone.1.unit2.body.conv2.bn.running_mean", "backbone.1.unit2.body.conv2.bn.running_var", "backbone.2.unit1.body.conv1.conv.weight", "backbone.2.unit1.body.conv1.bn.weight", "backbone.2.unit1.body.conv1.bn.bias", "backbone.2.unit1.body.conv1.bn.running_mean", "backbone.2.unit1.body.conv1.bn.running_var", "backbone.2.unit1.body.conv2.conv.weight", "backbone.2.unit1.body.conv2.bn.weight", "backbone.2.unit1.body.conv2.bn.bias", "backbone.2.unit1.body.conv2.bn.running_mean", "backbone.2.unit1.body.conv2.bn.running_var", "backbone.2.unit1.identity_conv.conv.weight", "backbone.2.unit1.identity_conv.bn.weight", "backbone.2.unit1.identity_conv.bn.bias", "backbone.2.unit1.identity_conv.bn.running_mean", "backbone.2.unit1.identity_conv.bn.running_var", "backbone.2.unit2.body.conv1.conv.weight", "backbone.2.unit2.body.conv1.bn.weight", "backbone.2.unit2.body.conv1.bn.bias", "backbone.2.unit2.body.conv1.bn.running_mean", "backbone.2.unit2.body.conv1.bn.running_var", "backbone.2.unit2.body.conv2.conv.weight", "backbone.2.unit2.body.conv2.bn.weight", "backbone.2.unit2.body.conv2.bn.bias", "backbone.2.unit2.body.conv2.bn.running_mean", "backbone.2.unit2.body.conv2.bn.running_var", "backbone.3.unit1.body.conv1.conv.weight", "backbone.3.unit1.body.conv1.bn.weight", "backbone.3.unit1.body.conv1.bn.bias", "backbone.3.unit1.body.conv1.bn.running_mean", "backbone.3.unit1.body.conv1.bn.running_var", "backbone.3.unit1.body.conv2.conv.weight", "backbone.3.unit1.body.conv2.bn.weight", "backbone.3.unit1.body.conv2.bn.bias", "backbone.3.unit1.body.conv2.bn.running_mean", "backbone.3.unit1.body.conv2.bn.running_var", "backbone.3.unit1.identity_conv.conv.weight", "backbone.3.unit1.identity_conv.bn.weight", "backbone.3.unit1.identity_conv.bn.bias", "backbone.3.unit1.identity_conv.bn.running_mean", "backbone.3.unit1.identity_conv.bn.running_var", "backbone.3.unit2.body.conv1.conv.weight", "backbone.3.unit2.body.conv1.bn.weight", "backbone.3.unit2.body.conv1.bn.bias", "backbone.3.unit2.body.conv1.bn.running_mean", "backbone.3.unit2.body.conv1.bn.running_var", "backbone.3.unit2.body.conv2.conv.weight", "backbone.3.unit2.body.conv2.bn.weight", "backbone.3.unit2.body.conv2.bn.bias", "backbone.3.unit2.body.conv2.bn.running_mean", "backbone.3.unit2.body.conv2.bn.running_var", "backbone.4.unit1.body.conv1.conv.weight", "backbone.4.unit1.body.conv1.bn.weight", "backbone.4.unit1.body.conv1.bn.bias", "backbone.4.unit1.body.conv1.bn.running_mean", "backbone.4.unit1.body.conv1.bn.running_var", "backbone.4.unit1.body.conv2.conv.weight", "backbone.4.unit1.body.conv2.bn.weight", "backbone.4.unit1.body.conv2.bn.bias", "backbone.4.unit1.body.conv2.bn.running_mean", "backbone.4.unit1.body.conv2.bn.running_var", "backbone.4.unit1.identity_conv.conv.weight", "backbone.4.unit1.identity_conv.bn.weight", "backbone.4.unit1.identity_conv.bn.bias", "backbone.4.unit1.identity_conv.bn.running_mean", "backbone.4.unit1.identity_conv.bn.running_var", "backbone.4.unit2.body.conv1.conv.weight", "backbone.4.unit2.body.conv1.bn.weight", "backbone.4.unit2.body.conv1.bn.bias", "backbone.4.unit2.body.conv1.bn.running_mean", "backbone.4.unit2.body.conv1.bn.running_var", "backbone.4.unit2.body.conv2.conv.weight", "backbone.4.unit2.body.conv2.bn.weight", "backbone.4.unit2.body.conv2.bn.bias", "backbone.4.unit2.body.conv2.bn.running_mean", "backbone.4.unit2.body.conv2.bn.running_var". 

Hi, thank you for your good code, recently I've tried to reproduce RevNet with PyTorch 1.11.0, and I use your code. However, I got a RunError as follows:

File ~\Documents\RevNet\revnet.py:71, in ReversibleBlockFunction.backward(ctx, grad_y)
     68 gm = ctx.gm
     70 with torch.autograd.set_detect_anomaly(True):
---> 71     x, y = ctx.saved_variables
     72 # x, y = ctx.saved_tensors
     73 y1, y2 = torch.chunk(y, chunks=2, dim=1)

RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.FloatTensor [0]], which is output 0 of ReversibleBlockFunctionBackward, is at version 3; expected version 2 instead. Hint: the backtrace further above shows the operation that failed to compute its gradient. The variable in question was changed in there or anywhere later. Good luck!

I've searched potential solution on the Internet but I still can not solve it. One solution is to downgrade the pytorch version to 1.4.0 but this version does not support the GPU I use. Could you provide some suggestions for me? I appreciate your help. Thanks!

Not sure if you would like me to do the same for all the other TF models, but I can. Also did not add unit tests, but this is also doable, just tell me.

pytorch now supports the XDG Base Directory specification https://github.com/pytorch/pytorch/issues/14693.

The pytorchcv module, provided by this repo is still using the hardcoded ~/.torch/models path.

You can see the "correct" logic for finding the .torch cache directory here.

PyramidNet's residual block(d) is not the same as pre-resnet's(a). It deletes the first ReLU and adds a new BN at the end. I noticed that in the pytorch version pyramidnet.py, the model is built just on pre_conv1x1_block. Waitting for your verification.

Hi thank you for wonderful DL networks repo.

I have one question to ask about pytorchcv

in pytorch/pytorchcv/models/squeezenext.py I found that SqueezeNext class has in_size argument but never being used.

I would like to modify my input img size form get_model function by changing in_size argument.

Is there any reason you are not using in_size argument currently?