diff --git a/Makefile b/Makefile
index f5524b90..3d3d5e43 100644
--- a/Makefile
+++ b/Makefile
@@ -3,7 +3,14 @@ CUDNN=0
 OPENCV=0
 DEBUG=0
 
-ARCH= --gpu-architecture=compute_52 --gpu-code=compute_52
+ARCH= -gencode arch=compute_20,code=[sm_20,sm_21] \
+      -gencode arch=compute_30,code=sm_30 \
+      -gencode arch=compute_35,code=sm_35 \
+      -gencode arch=compute_50,code=[sm_50,compute_50] \
+      -gencode arch=compute_52,code=[sm_52,compute_52]
+
+# This is what I use, uncomment if you know your arch and want to specify
+# ARCH=  -gencode arch=compute_52,code=compute_52
 
 VPATH=./src/
 EXEC=darknet
diff --git a/cfg/jnet19.cfg b/cfg/jnet19.cfg
new file mode 100644
index 00000000..bf73fb7b
--- /dev/null
+++ b/cfg/jnet19.cfg
@@ -0,0 +1,194 @@
+[net]
+batch=128
+subdivisions=1
+height=224
+width=224
+channels=3
+momentum=0.9
+decay=0.0005
+max_crop=448
+
+learning_rate=0.1
+policy=poly
+power=4
+max_batches=1600000
+
+[convolutional]
+batch_normalize=1
+filters=32
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+filters=1000
+size=1
+stride=1
+pad=1
+activation=linear
+
+[avgpool]
+
+[softmax]
+groups=1
+
+[cost]
+type=sse
+
diff --git a/cfg/jnet19_448.cfg b/cfg/jnet19_448.cfg
new file mode 100644
index 00000000..133c688e
--- /dev/null
+++ b/cfg/jnet19_448.cfg
@@ -0,0 +1,200 @@
+[net]
+batch=128
+subdivisions=4
+height=448
+width=448
+max_crop=512
+channels=3
+momentum=0.9
+decay=0.0005
+
+learning_rate=0.001
+policy=poly
+power=4
+max_batches=100000
+
+angle=7
+hue = .1
+saturation=.75
+exposure=.75
+aspect=.75
+
+[convolutional]
+batch_normalize=1
+filters=32
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+filters=1000
+size=1
+stride=1
+pad=1
+activation=linear
+
+[avgpool]
+
+[softmax]
+groups=1
+
+[cost]
+type=sse
+
diff --git a/src/batchnorm_layer.c b/src/batchnorm_layer.c
index 55bd3a8b..b53548bd 100644
--- a/src/batchnorm_layer.c
+++ b/src/batchnorm_layer.c
@@ -130,10 +130,10 @@ void forward_batchnorm_layer(layer l, network_state state)
         mean_cpu(l.output, l.batch, l.out_c, l.out_h*l.out_w, l.mean);
         variance_cpu(l.output, l.mean, l.batch, l.out_c, l.out_h*l.out_w, l.variance);
 
-        scal_cpu(l.out_c, .99, l.rolling_mean, 1);
-        axpy_cpu(l.out_c, .01, l.mean, 1, l.rolling_mean, 1);
-        scal_cpu(l.out_c, .99, l.rolling_variance, 1);
-        axpy_cpu(l.out_c, .01, l.variance, 1, l.rolling_variance, 1);
+        scal_cpu(l.out_c, .9, l.rolling_mean, 1);
+        axpy_cpu(l.out_c, .1, l.mean, 1, l.rolling_mean, 1);
+        scal_cpu(l.out_c, .9, l.rolling_variance, 1);
+        axpy_cpu(l.out_c, .1, l.variance, 1, l.rolling_variance, 1);
 
         copy_cpu(l.outputs*l.batch, l.output, 1, l.x, 1);
         normalize_cpu(l.output, l.mean, l.variance, l.batch, l.out_c, l.out_h*l.out_w);   
diff --git a/src/convolutional_kernels.cu b/src/convolutional_kernels.cu
index 709f77fb..ae9df8f0 100644
--- a/src/convolutional_kernels.cu
+++ b/src/convolutional_kernels.cu
@@ -133,6 +133,9 @@ void backward_convolutional_layer_gpu(convolutional_layer l, network_state state
 
     if(l.batch_normalize){
         backward_batchnorm_layer_gpu(l, state);
+        //axpy_ongpu(l.outputs*l.batch, -state.net.decay, l.x_gpu, 1, l.delta_gpu, 1);
+    } else {
+        //axpy_ongpu(l.outputs*l.batch, -state.net.decay, l.output_gpu, 1, l.delta_gpu, 1);
     }
     float *original_input = state.input;
 
diff --git a/src/parser.c b/src/parser.c
index 84733d7b..87a64919 100644
--- a/src/parser.c
+++ b/src/parser.c
@@ -966,23 +966,28 @@ void load_convolutional_weights(layer l, FILE *fp)
         //return;
     }
     int num = l.n*l.c*l.size*l.size;
-    if(0){
-        fread(l.biases + ((l.n != 1374)?0:5), sizeof(float), l.n, fp);
-        if (l.batch_normalize && (!l.dontloadscales)){
-            fread(l.scales + ((l.n != 1374)?0:5), sizeof(float), l.n, fp);
-            fread(l.rolling_mean + ((l.n != 1374)?0:5), sizeof(float), l.n, fp);
-            fread(l.rolling_variance + ((l.n != 1374)?0:5), sizeof(float), l.n, fp);
+    fread(l.biases, sizeof(float), l.n, fp);
+    if (l.batch_normalize && (!l.dontloadscales)){
+        fread(l.scales, sizeof(float), l.n, fp);
+        fread(l.rolling_mean, sizeof(float), l.n, fp);
+        fread(l.rolling_variance, sizeof(float), l.n, fp);
+        if(0){
+            int i;
+            for(i = 0; i < l.n; ++i){
+                printf("%g, ", l.rolling_mean[i]);
+            }
+            printf("\n");
+            for(i = 0; i < l.n; ++i){
+                printf("%g, ", l.rolling_variance[i]);
+            }
+            printf("\n");
         }
-        fread(l.weights + ((l.n != 1374)?0:5*l.c*l.size*l.size), sizeof(float), num, fp);
-    }else{
-        fread(l.biases, sizeof(float), l.n, fp);
-        if (l.batch_normalize && (!l.dontloadscales)){
-            fread(l.scales, sizeof(float), l.n, fp);
-            fread(l.rolling_mean, sizeof(float), l.n, fp);
-            fread(l.rolling_variance, sizeof(float), l.n, fp);
+        if(0){
+            fill_cpu(l.n, 0, l.rolling_mean, 1);
+            fill_cpu(l.n, 0, l.rolling_variance, 1);
         }
-        fread(l.weights, sizeof(float), num, fp);
     }
+    fread(l.weights, sizeof(float), num, fp);
     if(l.adam){
         fread(l.m, sizeof(float), num, fp);
         fread(l.v, sizeof(float), num, fp);