New DetectMultiBackend() class (#5549)

* New `DetectMultiBackend()` class * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * pb to pt fix * Cleanup * explicit apply_classifier path * Cleanup2 * Cleanup3 * Cleanup4 * Cleanup5 * Cleanup6 * val.py MultiBackend inference * warmup fix * to device fix * pt fix * device fix * Val cleanup * COCO128 URL to assets * half fix * detect fix * detect fix 2 * remove half from DetectMultiBackend * training half handling * training half handling 2 * training half handling 3 * Cleanup * Fix CI error * Add torchscript _extra_files * Add TorchScript * Add CoreML * CoreML cleanup * New `DetectMultiBackend()` class * pb to pt fix * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Cleanup * explicit apply_classifier path * Cleanup2 * Cleanup3 * Cleanup4 * Cleanup5 * Cleanup6 * val.py MultiBackend inference * warmup fix * to device fix * pt fix * device fix * Val cleanup * COCO128 URL to assets * half fix * detect fix * detect fix 2 * remove half from DetectMultiBackend * training half handling * training half handling 2 * training half handling 3 * Cleanup * Fix CI error * Add torchscript _extra_files * Add TorchScript * Add CoreML * CoreML cleanup * revert default to pt * Add Usage examples * Cleanup val Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2021-11-09 16:45:02 +01:00
1 parent 79bca2bf64
commit 3883261143
@@ -17,7 +17,6 @@ import torch
 import torch.distributed as dist
 import torch.nn as nn
 import torch.nn.functional as F
-import torchvision

 from utils.general import LOGGER

@@ -235,25 +234,6 @@ def model_info(model, verbose=False, img_size=640):
    LOGGER.info(f"Model Summary: {len(list(model.modules()))} layers, {n_p} parameters, {n_g} gradients{fs}")


-def load_classifier(name='resnet101', n=2):
-    # Loads a pretrained model reshaped to n-class output
-    model = torchvision.models.__dict__[name](pretrained=True)
-
-    # ResNet model properties
-    # input_size = [3, 224, 224]
-    # input_space = 'RGB'
-    # input_range = [0, 1]
-    # mean = [0.485, 0.456, 0.406]
-    # std = [0.229, 0.224, 0.225]
-
-    # Reshape output to n classes
-    filters = model.fc.weight.shape[1]
-    model.fc.bias = nn.Parameter(torch.zeros(n), requires_grad=True)
-    model.fc.weight = nn.Parameter(torch.zeros(n, filters), requires_grad=True)
-    model.fc.out_features = n
-    return model
-
-
 def scale_img(img, ratio=1.0, same_shape=False, gs=32):  # img(16,3,256,416)
    # scales img(bs,3,y,x) by ratio constrained to gs-multiple
    if ratio == 1.0: