Home
last modified time | relevance | path

Searched refs:num_class (Results 1 – 25 of 246) sorted by relevance

12345678910

/dports/misc/tvm/incubator-tvm-0.6.1/tests/python/frontend/mxnet/model_zoo/
H A D__init__.py25 num_class = 10
26 return mlp.get_symbol(num_class)
29 num_class = 10
30 return tvm.relay.testing.mlp.get_workload(1, num_class)[0]
34 num_class = 1000
35 return vgg.get_symbol(num_class, num_layers)
38 num_class = 1000
40 1, num_class, num_layers=num_layers)[0]
44 num_class = 1000
48 num_class = 1000
[all …]
/dports/misc/mxnet/incubator-mxnet-1.9.0/3rdparty/tvm/tests/python/frontend/mxnet/model_zoo/
H A D__init__.py25 num_class = 10
26 return mlp.get_symbol(num_class)
30 num_class = 10
31 return tvm.relay.testing.mlp.get_workload(1, num_class)[0]
36 num_class = 1000
37 return vgg.get_symbol(num_class, num_layers)
41 num_class = 1000
42 return tvm.relay.testing.vgg.get_workload(1, num_class, num_layers=num_layers)[0]
47 num_class = 1000
48 return resnet.get_symbol(num_class, num_layers, "3,224,224")
[all …]
/dports/misc/py-tvm/incubator-tvm-0.6.1/tests/python/frontend/mxnet/model_zoo/
H A D__init__.py25 num_class = 10
26 return mlp.get_symbol(num_class)
29 num_class = 10
30 return tvm.relay.testing.mlp.get_workload(1, num_class)[0]
34 num_class = 1000
35 return vgg.get_symbol(num_class, num_layers)
38 num_class = 1000
40 1, num_class, num_layers=num_layers)[0]
44 num_class = 1000
48 num_class = 1000
[all …]
/dports/misc/py-gluoncv/gluon-cv-0.9.0/gluoncv/model_zoo/rcnn/
H A Drcnn.py71 self.num_class = len(classes)
80 assert self.num_class > 0, "Invalid number of class : {}".format(self.num_class)
92 self.num_class + 1, weight_initializer=mx.init.Normal(0.01))
94 self.num_class * 4, weight_initializer=mx.init.Normal(0.001))
95 self.cls_decoder = MultiPerClassDecoder(num_class=self.num_class + 1)
169 self.num_class = len(classes)
208 self.num_class + 1, weight_initializer=mx.init.Normal(0.01),
211 self.num_class * 4, weight_initializer=mx.init.Normal(0.001),
213 self.cls_decoder = MultiPerClassDecoder(num_class=self.num_class + 1)
/dports/misc/py-xgboost/xgboost-1.5.1/src/objective/
H A Dmulticlass_obj.cu32 int num_class; member
35 DMLC_DECLARE_FIELD(num_class).set_lower_bound(1) in DMLC_DECLARE_PARAMETER()
58 CHECK(preds.Size() == (static_cast<size_t>(param_.num_class) * info.labels_.Size())) in GetGradient()
61 << info.labels_.Size() * static_cast<size_t>(param_.num_class) << "\n" in GetGradient()
62 << "num_class: " << param_.num_class << "\n" in GetGradient()
65 const int nclass = param_.num_class; in GetGradient()
135 const int nclass = param_.num_class; in Transform()
/dports/misc/xgboost/xgboost-1.5.1/src/objective/
H A Dmulticlass_obj.cu32 int num_class; member
35 DMLC_DECLARE_FIELD(num_class).set_lower_bound(1) in DMLC_DECLARE_PARAMETER()
58 CHECK(preds.Size() == (static_cast<size_t>(param_.num_class) * info.labels_.Size())) in GetGradient()
61 << info.labels_.Size() * static_cast<size_t>(param_.num_class) << "\n" in GetGradient()
62 << "num_class: " << param_.num_class << "\n" in GetGradient()
65 const int nclass = param_.num_class; in GetGradient()
135 const int nclass = param_.num_class; in Transform()
/dports/misc/py-xgboost/xgboost-1.5.1/R-package/man/
H A Dpredict.xgb.Booster.Rd70 For multiclass classification, either a \code{num_class * nrows(newdata)} vector or
71 a \code{(nrows(newdata), num_class)} dimension matrix is returned, depending on
79 For a multiclass case, a list of \code{num_class} elements is returned, where each element is
88 For a multiclass case, a list of \code{num_class} elements is returned, where each element is
92 normal prediction, the output is a 2-dimension array \code{(num_class, nrow(newdata))}.
162 num_class <- 3
166 objective = "multi:softprob", num_class = num_class)
167 # predict for softmax returns num_class probability numbers per case:
170 # reshape it to a num_class-columns matrix
171 pred <- matrix(pred, ncol=num_class, byrow=TRUE)
[all …]
/dports/misc/xgboost/xgboost-1.5.1/R-package/man/
H A Dpredict.xgb.Booster.Rd70 For multiclass classification, either a \code{num_class * nrows(newdata)} vector or
71 a \code{(nrows(newdata), num_class)} dimension matrix is returned, depending on
79 For a multiclass case, a list of \code{num_class} elements is returned, where each element is
88 For a multiclass case, a list of \code{num_class} elements is returned, where each element is
92 normal prediction, the output is a 2-dimension array \code{(num_class, nrow(newdata))}.
162 num_class <- 3
166 objective = "multi:softprob", num_class = num_class)
167 # predict for softmax returns num_class probability numbers per case:
170 # reshape it to a num_class-columns matrix
171 pred <- matrix(pred, ncol=num_class, byrow=TRUE)
[all …]
/dports/misc/py-xgboost/xgboost-1.5.1/R-package/R/
H A Dcallbacks.R492 if (env$num_class > 1) {
493 matrix(NA_real_, N, env$num_class)
718 num_class <- n - 1 functionVar
719 num_feat <- (length(dmp) - 4) / num_class
724 num_class <- NVL(model$params$num_class, 1)
731 num_class > 1 &&
732 (class_index[1] < 0 || class_index[1] >= num_class))
733 stop("class_index has to be within [0,", num_class - 1, "]")
736 if (!is.null(class_index) && num_class > 1) {
739 function(x) x[, seq(1 + class_index, by = num_class, length.out = num_feat)])
[all …]
/dports/misc/xgboost/xgboost-1.5.1/R-package/R/
H A Dcallbacks.R492 if (env$num_class > 1) {
493 matrix(NA_real_, N, env$num_class)
718 num_class <- n - 1 functionVar
719 num_feat <- (length(dmp) - 4) / num_class
724 num_class <- NVL(model$params$num_class, 1)
731 num_class > 1 &&
732 (class_index[1] < 0 || class_index[1] >= num_class))
733 stop("class_index has to be within [0,", num_class - 1, "]")
736 if (!is.null(class_index) && num_class > 1) {
739 function(x) x[, seq(1 + class_index, by = num_class, length.out = num_feat)])
[all …]
/dports/misc/py-gluoncv/gluon-cv-0.9.0/gluoncv/model_zoo/yolo/
H A Dyolo_target.py24 def __init__(self, num_class, **kwargs): argument
26 self._num_class = num_class
162 def __init__(self, num_class, ignore_iou_thresh, **kwargs): argument
164 self._num_class = num_class
215 def __init__(self, num_class, ignore_iou_thresh, **kwargs): argument
217 self._num_class = num_class
218 self._dynamic_target = YOLOV3DynamicTargetGeneratorSimple(num_class, ignore_iou_thresh)
/dports/graphics/vapoursynth-waifu2x-ncnn-vulkan/vapoursynth-waifu2x-ncnn-vulkan-r4/deps/ncnn/src/layer/x86/
H A Dyolov3detectionoutput_x86.cpp52 if (channels_per_box != 4 + 1 + num_class) in forward()
77 Mat scores = bottom_top_blobs.channel_range(p + 5, num_class); in forward()
94 for (int q = 0; q < num_class; q++) in forward()
108 float* end = ptr + num_class * cs; in forward()
111 float* end8 = ptr + (num_class & -8) * cs; in forward()
/dports/graphics/waifu2x-ncnn-vulkan/waifu2x-ncnn-vulkan-20210521/src/ncnn/src/layer/x86/
H A Dyolov3detectionoutput_x86.cpp52 if (channels_per_box != 4 + 1 + num_class) in forward()
77 Mat scores = bottom_top_blobs.channel_range(p + 5, num_class); in forward()
94 for (int q = 0; q < num_class; q++) in forward()
108 float* end = ptr + num_class * cs; in forward()
111 float* end8 = ptr + (num_class & -8) * cs; in forward()
/dports/benchmarks/vkpeak/vkpeak-20210430/ncnn/src/layer/x86/
H A Dyolov3detectionoutput_x86.cpp52 if (channels_per_box != 4 + 1 + num_class) in forward()
77 Mat scores = bottom_top_blobs.channel_range(p + 5, num_class); in forward()
94 for (int q = 0; q < num_class; q++) in forward()
108 float* end = ptr + num_class * cs; in forward()
111 float* end8 = ptr + (num_class & -8) * cs; in forward()
/dports/misc/ncnn/ncnn-20211208/src/layer/x86/
H A Dyolov3detectionoutput_x86.cpp52 if (channels_per_box != 4 + 1 + num_class) in forward()
77 Mat scores = bottom_top_blobs.channel_range(p + 5, num_class); in forward()
94 for (int q = 0; q < num_class; q++) in forward()
108 float* end = ptr + num_class * cs; in forward()
111 float* end8 = ptr + (num_class & -8) * cs; in forward()
/dports/graphics/realsr-ncnn-vulkan/realsr-ncnn-vulkan-20210210/src/ncnn/src/layer/x86/
H A Dyolov3detectionoutput_x86.cpp52 if (channels_per_box != 4 + 1 + num_class) in forward()
77 Mat scores = bottom_top_blobs.channel_range(p + 5, num_class); in forward()
94 for (int q = 0; q < num_class; q++) in forward()
108 float* end = ptr + num_class * cs; in forward()
111 float* end8 = ptr + (num_class & -8) * cs; in forward()
/dports/misc/mxnet/incubator-mxnet-1.9.0/example/ssd/
H A Devaluate.py83 num_class = args.num_class variable
91 assert len(class_names) == num_class
102 evaluate_net(network, args.rec_path, num_class, args.num_batch,
/dports/misc/py-mxnet/incubator-mxnet-1.9.0/example/ssd/
H A Devaluate.py83 num_class = args.num_class variable
91 assert len(class_names) == num_class
102 evaluate_net(network, args.rec_path, num_class, args.num_batch,
/dports/misc/mxnet/incubator-mxnet-1.9.0/example/image-classification/
H A Dsymbol_resnet-v2.R83 resnet <- function(units, num_stage, filter_list, num_class, bottle_neck=TRUE, argument
120 fc1 <- mx.symbol.FullyConnected(data=flat, num_hidden=num_class, name='fc1')
125 get_symbol <- function(num_class, depth=18){ argument
154 num_class=num_class, bottle_neck=bottle_neck,
/dports/misc/py-mxnet/incubator-mxnet-1.9.0/example/image-classification/
H A Dsymbol_resnet-v2.R83 resnet <- function(units, num_stage, filter_list, num_class, bottle_neck=TRUE, argument
120 fc1 <- mx.symbol.FullyConnected(data=flat, num_hidden=num_class, name='fc1')
125 get_symbol <- function(num_class, depth=18){ argument
154 num_class=num_class, bottle_neck=bottle_neck,
/dports/misc/py-xgboost/xgboost-1.5.1/R-package/tests/testthat/
H A Dtest_model_compatibility.R40 testthat::expect_equal(as.numeric(config$learner$learner_model_param$num_class),
44 testthat::expect_equal(as.numeric(config$learner$learner_model_param$num_class), 0)
48 testthat::expect_equal(as.numeric(config$learner$learner_model_param$num_class), 0)
/dports/misc/xgboost/xgboost-1.5.1/R-package/tests/testthat/
H A Dtest_model_compatibility.R40 testthat::expect_equal(as.numeric(config$learner$learner_model_param$num_class),
44 testthat::expect_equal(as.numeric(config$learner$learner_model_param$num_class), 0)
48 testthat::expect_equal(as.numeric(config$learner$learner_model_param$num_class), 0)
/dports/misc/py-mxnet/incubator-mxnet-1.9.0/tests/nightly/
H A Dtest_tlocal_racecondition.py44 num_class = len(class_names) variable
63 return train_iter, val_iter, class_names, num_class
65 train_data, test_data, class_names, num_class = get_iterators( variable
/dports/misc/mxnet/incubator-mxnet-1.9.0/tests/nightly/
H A Dtest_tlocal_racecondition.py44 num_class = len(class_names) variable
63 return train_iter, val_iter, class_names, num_class
65 train_data, test_data, class_names, num_class = get_iterators( variable
/dports/misc/py-gluoncv/gluon-cv-0.9.0/gluoncv/auto/estimators/image_classification/
H A Dimage_classification.py76 if not self.classes or not self.num_class:
211 if not self.num_class:
214 assert len(self.classes) == self.num_class
246 kwargs = {'ctx': self.ctx, 'pretrained': False, 'classes': self.num_class}
270 new_fc_layer = gluon.nn.Dense(self.num_class, in_units=in_channels)
272 … new_fc_layer = gluon.nn.Conv2D(self.num_class, in_channels=in_channels, kernel_size=1)
288 …lf._cfg.train.teacher is not None and self._cfg.train.hard_weight < 1.0 and self.num_class == 1000:
290 … self.teacher = get_model(teacher_name, pretrained=True, classes=self.num_class, ctx=self.ctx)
346 acc_top5 = mx.metric.TopKAccuracy(min(5, self.num_class))
392 topK = min(5, self.num_class)

12345678910